An FTTR network resource planning method, system, device and medium

Abstract

The application discloses an FTTR network resource planning method, system, device and medium, relates to the technical field of network, and the method comprises the following steps: determining a target terminal according to the current position information; determining a signal strength sequence according to the current position information, and determining a target node according to the signal strength sequence; acquiring the current network speed and behavior data of each user terminal, and determining a target network speed sequence according to the current network speed and the behavior data; setting a bandwidth constraint condition and a performance constraint condition, calling a network speed prediction model, and determining a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm; converting the network access node of the target terminal into the target node, and adjusting the bandwidth of each network node to the corresponding planning bandwidth according to the planning bandwidth sequence. The application has the effect of improving the flexibility of the FTTR network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of networks, in particular to an FTTR network resource planning method, system, device and medium. BACKGROUND

[0002] FTTR (Fiber to the Room) and FTTR B (Building / Broadband) technologies aim to meet the growing demand for high-speed internet connectivity in modern homes and business environments. FTTR provides ultra-low latency and high-bandwidth network services by connecting optical fibers directly to each room, ensuring users have an excellent experience in various applications such as high-definition video streaming, online gaming, and remote work. FTTR B emphasizes the effectiveness of fiber cabling within buildings, especially in multi-family homes and commercial buildings, to ensure comprehensive coverage and reliable broadband access. The combination of the two provides a solid network foundation for smart homes and smart cities, driving digital transformation and efficient use of resources.

[0003] In terms of network bandwidth resource planning, current FTTR networks often use fixed allocation methods. This method cannot dynamically adjust according to the real needs of users, which may lead to insufficient bandwidth for optical modems, and may also cause idle bandwidth resources for optical modems. In addition, due to the lack of real-time monitoring and traffic analysis functions, network managers have difficulty effectively optimizing bandwidth configuration, which affects user experience.

[0004] Therefore, the FTTR network has problems such as inflexible bandwidth resource allocation and difficulty in network adjustment in specific implementation, resulting in relatively low flexibility and intelligence level of the FTTR network, making it difficult to fully adapt to users' changing network needs. SUMMARY

[0005] In order to improve the flexibility of the FTTR network, the present application provides an FTTR network resource planning method, system, device and medium.

[0006] In a first aspect, the present application provides an FTTR network resource planning method, which adopts the following technical solution:

[0007] An FTTR network resource planning method, comprising:

[0008] Monitoring the current location information of each user terminal in the FTTR network according to a preset frequency, and determining a target terminal according to the current location information, wherein the target terminal is a user terminal whose distance between the current location and the last collected location exceeds a preset distance;

[0009] determining a signal strength sequence according to the current position information, and determining a target node according to the signal strength sequence, wherein the signal strength sequence comprises signal strengths of the target terminal to each network node, and the each network node at least comprises a master optical CATV and a slave optical CATV;

[0010] obtaining current network speeds and behavior data of the each user terminal, and determining a target network speed sequence according to the current network speeds and the behavior data, wherein the target network speed sequence comprises target network speeds adapted to behaviors of the each user terminal;

[0011] setting a bandwidth constraint condition and a performance constraint condition, calling a network speed prediction model, and determining a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm, so that differences between predicted network speeds of the each network node and the target network speed are within a preset range, wherein the planning bandwidth sequence comprises planning bandwidths of the each network node, and the planning performance sequence comprises planning performances corresponding to the planning bandwidths of the each network node;

[0012] converting an online node of the target terminal to the target node, and adjusting bandwidths of the each network node to corresponding planning bandwidths according to the planning bandwidth sequence.

[0013] By adopting the technical scheme, the current position information of each user terminal in the FTTR network is monitored according to a preset frequency, and a target terminal is determined according to the current position information, wherein the target terminal is a user terminal whose distance between the current position and the last collected position exceeds a preset distance; then a signal strength sequence is determined according to the current position information, and a target node is determined according to the signal strength sequence, wherein the signal strength sequence includes the signal strength of the target terminal to each network node, and each network node at least includes a master optical modem and a slave optical modem; then the current network speed and behavior data of each user terminal are obtained, and a target network speed sequence is determined according to the current network speed and behavior data, wherein the target network speed sequence includes the target network speed of each user terminal that is adapted to the behavior; then a bandwidth constraint condition and a performance constraint condition are set, a network speed prediction model is called, and a planned bandwidth sequence and a planned performance sequence corresponding to the planned bandwidth sequence are determined according to a gradient descent algorithm, so that the difference between the predicted network speed of each network node and the target network speed is within a preset range, wherein the planned bandwidth sequence includes the planned bandwidth of each network node, and the planned performance sequence includes the planned performance corresponding to the planned bandwidth of each network node; finally, the online node of the target terminal is converted into the target node, and the bandwidth of each network node is adjusted to the corresponding planned bandwidth according to the planned bandwidth sequence. Through the above method, when the user moves, the online node of the user terminal can be automatically switched according to the signal strength, the bandwidth of each network node is re-planned, and the network speed of each user network terminal in the FTTR network is kept from fluctuating greatly, thereby improving the user experience and improving the flexibility and intelligent level of the FTTR network, which can better meet the increasingly changing network demand.

[0014] Optionally, the step of determining the signal strength sequence according to the current position information comprises:

[0015] obtaining position information of the network nodes, and determining a distance sequence according to the position information and the current position, wherein the distance sequence includes the distance between the target terminal and the network nodes;

[0016] determining the signal strength sequence based on a signal strength prediction model and according to the distance sequence.

[0017] By adopting the technical scheme, in order to determine the signal strength sequence, the position information of each network node is obtained, and a distance sequence is determined according to the position information and the current position, wherein the distance sequence includes the distance between the target terminal and each network node, and then the signal strength sequence is determined based on a signal strength prediction model and according to the distance sequence.

[0018] Optionally, the step of determining the target network speed sequence according to the current network speed and the behavior data comprises:

[0019] For each user terminal, a target behavior category corresponding to the user terminal and a cumulative number corresponding to the target behavior category are determined according to the behavior data;

[0020] The target behavior category is matched in a preset table to obtain a target demand network speed corresponding to the target behavior category, wherein the preset table includes the user behavior category data and demand network speed data, and the preset table is used to represent a mapping relationship between the user behavior category data and the demand network speed data;

[0021] A demand network speed sum of the user terminal is calculated according to the demand network speed and the cumulative number, and it is determined whether the current network speed is greater than the demand network speed sum; if yes, the current network speed is taken as a target network speed of the user terminal, and if no, the demand network speed sum is taken as the target network speed of the user terminal;

[0022] A target network speed sequence is generated according to the target network speed of each user terminal.

[0023] By adopting the technical solution, in order to determine a target network speed sequence, for each user terminal, a target behavior category corresponding to the user terminal and a cumulative number corresponding to the target behavior category are determined according to behavior data, then the target behavior category is matched in a preset table to obtain a target demand network speed corresponding to the target behavior category, wherein the preset table includes the user behavior category data and demand network speed data, and the preset table is used to represent a mapping relationship between the user behavior category data and the demand network speed data, then a demand network speed sum of the user terminal is calculated according to the demand network speed and the cumulative number, and it is determined whether the current network speed is greater than the demand network speed sum; if yes, the current network speed is taken as a target network speed of the user terminal, and if no, the demand network speed sum is taken as the target network speed of the user terminal, and finally a target network speed sequence is generated according to the target network speed of each user terminal.

[0024] Optionally, the method for generating the network speed prediction model comprises:

[0025] An evaluation parameter set is obtained, wherein the evaluation parameter set includes first historical bandwidth data and first historical performance data corresponding to the first historical bandwidth data;

[0026] Pearson coefficients between parameters in the evaluation parameter set are calculated, and mutual exclusivity between the parameters in the evaluation parameter set is evaluated according to the Pearson coefficients, to determine a mutually exclusive parameter group;

[0027] Linear transformation is performed on the mutually exclusive parameter group to obtain corresponding merged parameters;

[0028] An initial decision tree model is obtained by performing model construction based on a decision tree algorithm and according to the merged parameters and the evaluation parameter set.

[0029] training and testing the initial decision tree model according to the model training data, to obtain the network speed prediction model.

[0030] By adopting the technical scheme, in order to generate the network speed prediction model, an evaluation parameter set is obtained, wherein the evaluation parameter set includes first historical bandwidth data and first historical performance data corresponding to the first historical bandwidth data, then a Pearson coefficient between each parameter in the evaluation parameter set is calculated, and mutual exclusivity between each parameter in the evaluation parameter set is evaluated according to the Pearson coefficient, a mutually exclusive parameter group is determined, then linear transformation is performed on the mutually exclusive parameter group to obtain corresponding merged parameters, then an initial decision tree model is obtained by constructing a model based on a decision tree algorithm and according to the merged parameters and the evaluation parameter set, and finally, the initial decision tree model is trained and tested according to model training data, to obtain the network speed prediction model.

[0031] Optionally, the step of training and testing the initial decision tree model according to the model training data, to obtain the network speed prediction model, includes:

[0032] obtaining model training data, wherein the model training data includes second historical bandwidth data, second historical performance data corresponding to the second historical bandwidth data, and historical network speed data, and the model training data is divided into a training set and a test set according to a preset ratio;

[0033] setting hyperparameters of the initial decision tree model according to a genetic algorithm, and setting a root mean square error (RMSE) and a determination coefficient (R 2 as evaluation indexes;

[0034] training the initial decision tree model according to the training set, to obtain a trained decision tree model;

[0035] testing the trained decision tree model according to the test set, and determining whether errors are within a preset range according to the evaluation indexes, if yes, taking the trained decision tree model as the network speed prediction model.

[0036] By adopting the technical scheme, in order to realize the training and testing of the initial decision tree model, the model training data is acquired first, the model training data includes the second historical bandwidth data, the second historical performance data corresponding to the second historical bandwidth data and the historical network speed data, the model training data is divided into a training set and a test set according to a preset ratio, then the hyperparameters of the initial decision tree model are set according to the genetic algorithm, and the root mean square error RMSE and the determination coefficient R2 are taken as evaluation indexes, then the initial decision tree model is trained according to the training set, to obtain a trained decision tree model, finally the trained decision tree model is tested according to the test set, and whether the errors are all within a preset range is judged according to the evaluation indexes, if yes, the trained decision tree model is taken as a network speed prediction model.

[0037] Optionally, after the step of testing the trained decision tree model according to the test set, and judging whether the errors are all within a preset range according to the evaluation indexes, if yes, the trained decision tree model is taken as a network speed prediction model, the step further includes:

[0038] acquiring target bandwidth data and target performance data, wherein the target performance data includes a target packet loss rate, a target throughput, a target connection number and a target delay;

[0039] inputting the target bandwidth data and the performance data into the network speed prediction model to obtain corresponding predicted network speed.

[0040] By adopting the technical scheme, in order to realize the prediction of the network speed, the target bandwidth data and the target performance data are acquired first, wherein the target performance data includes a target packet loss rate, a target throughput, a target connection number and a target delay, then the target bandwidth data and the performance data are inputted into the network speed prediction model to obtain corresponding predicted network speed.

[0041] Optionally, the step of determining a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to the gradient descent algorithm, so that the network speed of each network node is closest to the target network speed, includes:

[0042] acquiring a merging logic of the merging parameters, and defining a search parameter space according to the merging logic, the bandwidth constraint condition and the performance constraint condition;

[0043] performing search space mapping according to the merging parameters and the evaluation parameter set, and defining a parameter space distance according to Euclidean distance;

[0044] setting an initial search value and an initial search direction, and setting an initial search;

[0045] according to an iteration point and a search direction iterating, wherein, is the k+1th iteration point, is the kth iteration point, is the search step length, is the search direction of the kth iteration point, is the search direction of the k+1th iteration point, is the update factor of the kth iteration point, is the gradient in the Euclidean space;

[0046] performing network speed prediction according to the network speed prediction model to obtain a prediction result, and determining whether a termination condition is met according to the prediction result, if yes, indicating that the planning bandwidth of each network node and the planning performance corresponding to the planning bandwidth are searched;

[0047] generating a planning bandwidth sequence according to the planning bandwidth of each network node, and generating a planning performance sequence according to the planning performance of each network node.

[0048] By adopting the above technical solution, in order to determine the planning bandwidth sequence and the planning performance sequence corresponding to the planning bandwidth sequence, the merging logic of the merging parameter is first obtained, and then the search parameter space is defined according to the merging logic, the bandwidth constraint condition and the performance constraint condition. Then, the search space mapping is performed according to the merging parameter and the evaluation parameter set, and the parameter space distance is defined according to the Euclidean distance. Then, the initial search value and the initial search direction are set, and the initial search is set. Then, the iteration point and the search direction are iterated, wherein, is the k+1th iteration point, is the kth iteration point, is the search step length, is the search direction of the kth iteration point, is the search direction of the k+1th iteration point, is the update factor of the kth iteration point, is the gradient in the Euclidean space, then network speed prediction is performed according to the network speed prediction model to obtain a prediction result, and whether a termination condition is met is determined according to the prediction result, if yes, indicating that the planning bandwidth of each network node and the planning performance corresponding to the planning bandwidth are searched, and finally a planning bandwidth sequence is generated according to the planning bandwidth of each network node, and a planning performance sequence is generated according to the planning performance of each network node.

[0049] In a second aspect, the present application also provides an FTTR network resource planning system, which adopts the following technical solution:

[0050] An FTTR network resource planning system, comprising:

[0051] a target terminal determination module, configured to monitor current position information of each user terminal in the FTTR network according to a preset frequency, and determine a target terminal according to the current position information, wherein the target terminal is a user terminal whose distance between a current position and a last collected position exceeds a preset distance;

[0052] a target node determination module, configured to determine a signal strength sequence according to the current position information, and determine a target node according to the signal strength sequence, wherein the signal strength sequence comprises signal strengths of the target terminal to each network node, and the each network node at least comprises a master optical modem and a slave optical modem;

[0053] a target network speed sequence determination module, configured to acquire current network speeds and behavior data of the each user terminal, and determine a target network speed sequence according to the current network speeds and the behavior data, wherein the target network speed sequence comprises target network speeds adapted to behaviors of the each user terminal;

[0054] a planning module, configured to set a bandwidth constraint condition and a performance constraint condition, call a network speed prediction model, and determine a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm, so that a difference between a predicted network speed of each network node and a target network speed is within a preset range, wherein the planning bandwidth sequence comprises planning bandwidths of the each network node, and the planning performance sequence comprises planning performances corresponding to the planning bandwidths of the each network node;

[0055] a network adjustment module, configured to convert an online node of the target terminal to the target node, and adjust bandwidths of the each network node to corresponding planning bandwidths according to the planning bandwidth sequence.

[0056] In a third aspect, a computer device is also provided, which adopts the technical scheme as follows:

[0057] A computer device comprises a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements the method in the first aspect when executing the computer program.

[0058] In a fourth aspect, a computer readable storage medium is also provided, which adopts the technical scheme as follows:

[0059] A computer readable storage medium stores a computer program capable of being loaded and executed by a processor to implement the method in the first aspect.

[0060] In summary, the present application at least includes the following beneficial technical effects: first, the current position information of each user terminal in the FTTR network is monitored according to the preset frequency, and the target terminal is determined according to the current position information, wherein the target terminal is a user terminal whose distance between the current position and the last collected position exceeds the preset distance; then, the signal strength sequence is determined according to the current position information, and the target node is determined according to the signal strength sequence, wherein the signal strength sequence includes the signal strength of the target terminal to each network node, and each network node at least includes the master optical modem and the slave optical modem; then, the current network speed and behavior data of each user terminal are obtained, and the target network speed sequence is determined according to the current network speed and behavior data, wherein the target network speed sequence includes the target network speed of each user terminal adapted to the behavior; then, the bandwidth constraint condition and the performance constraint condition are set, the network speed prediction model is called, and the planning bandwidth sequence and the planning performance sequence corresponding to the planning bandwidth sequence are determined according to the gradient descent algorithm, so that the difference between the predicted network speed of each network node and the target network speed is within the preset range, wherein the planning bandwidth sequence includes the planning bandwidth of each network node, and the planning performance sequence includes the planning performance corresponding to the planning bandwidth of each network node; finally, the online node of the target terminal is converted into the target node, and the bandwidth of each network node is adjusted to the corresponding planning bandwidth according to the planning bandwidth sequence. Through the above method, when the user moves, the online node of the user terminal can be automatically switched according to the signal strength, the bandwidth of each network node is re-planned, and the network speed of each user network terminal in the FTTR network is kept from fluctuating greatly, thereby improving the user experience, and improving the flexibility and intelligent level of the FTTR network, which can better meet the increasingly changing network demand. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 is a whole flow schematic diagram of the embodiment of the present application.

[0062] Figure 2 is a structure schematic diagram of the system of the present application.

[0063] Figure 3 is a structure block diagram of the computer equipment of the present application. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0065] The embodiment of the present application discloses a FTTR network resource planning method.

[0066] Reference Figure 1The application discloses an FTTR network resource planning method.

[0067] Step S11, monitoring current position information of each user terminal in the FTTR network according to a preset frequency, and determining a target terminal according to the current position information.

[0068] The target terminal is a user terminal whose distance between the current position and the last collected position exceeds a preset distance.

[0069] It should be noted that in step S11, the positioning information of all user terminals in the FTTR network can be periodically (for example, every minute or every 10 seconds) monitored, and the user terminals are precisely positioned by using GPS, Wi-Fi or other positioning technologies, then the current collected position is compared with the last collected position, the distance is calculated, and if the distance exceeds a preset distance (for example, 5 meters or 10 meters), the user terminal is marked as a target terminal. The Euclidean distance between the positions of the user terminals can be calculated by using a formula, and the efficiency is ensured.

[0070] Step S12, determining a signal strength sequence according to the current position information, and determining a target node according to the signal strength sequence.

[0071] The signal strength sequence includes signal strengths of the target terminal to each network node, and each network node at least includes a master optical modem and a slave optical modem.

[0072] It should be noted that in step S12, the signal strengths of the target terminal to the master optical modem and each slave optical modem are calculated and recorded in real time, data is collected by using a network management tool or an SNMP protocol, and all signal strength data is arranged into a sequence. The nodes with the strongest signal strengths can be selected as target nodes according to the order from high to low of the intensity values, and the network connection quality is ensured to be optimal.

[0073] Step S13, acquiring current network speeds and behavior data of each user terminal, and determining a target network speed sequence according to the current network speeds and behavior data.

[0074] The target network speed sequence includes target network speeds of each user terminal that are adapted to behaviors of the user terminals.

[0075] It should be noted that in step S13, the system acquires current actual network speeds and network behavior data (for example, specific application types such as a video conference, file downloading or web browsing) of each user terminal in real time, and according to a set of preset strategies aiming at optimizing the overall experience, an ideal target network speed that is most matched with the current behavior of each terminal is intelligently calculated and set for each terminal. Finally, the personalized target network speed values of all terminals are combined into an ordered set, that is, a target network speed sequence on which subsequent bandwidth allocation is based is formed.

[0076] Step S14, set bandwidth constraints and performance constraints, call the network speed prediction model, and determine the planning bandwidth sequence and the planning performance sequence corresponding to the planning bandwidth sequence according to the gradient descent algorithm, so that the difference between the predicted network speed of each network node and the target network speed is within the preset range.

[0077] The planning bandwidth sequence includes the planning bandwidth of each network node, and the planning performance sequence includes the planning performance corresponding to the planning bandwidth of each network node.

[0078] It should be noted that in step S14, the lower limit and upper limit of the bandwidth (such as min 2 Mbps, max 100 Mbps) are set according to the network demand, user demand and user's network package, and the upper limit and lower limit of each performance index are set according to the configuration of each network node, the fixed limit range of performance, etc., then the network speed prediction model is established by using machine learning algorithm (such as linear regression or deep learning), the historical network speed and other related factors are input for training, and finally the gradient descent algorithm is applied to optimize the bandwidth allocation, and the planning bandwidth sequence is adjusted each time to make the adjusted network speed as close as possible to the target network speed.

[0079] Step S15, convert the online node of the target terminal into the target node, and adjust the bandwidth of each network node to the corresponding planning bandwidth according to the planning bandwidth sequence.

[0080] It should be noted that in step S15, the network connection of the target terminal is set to the target node identified in step S12, ensuring that the new network connection takes effect, and adjusting the bandwidth of each network node according to the planning bandwidth sequence through the network manager (such as network control protocol or SNMP) until the planning bandwidth setting is met.

[0081] In the above embodiment, the current position information of each user terminal in the FTTR network is first monitored at a preset frequency, and a target terminal is determined according to the current position information, wherein the target terminal is a user terminal whose distance between the current position and the last collected position exceeds a preset distance, then a signal strength sequence is determined according to the current position information, and a target node is determined according to the signal strength sequence, wherein the signal strength sequence includes the signal strength of the target terminal to each network node, and each network node at least includes a master optical modem and a slave optical modem, then the current network speed and behavior data of each user terminal are obtained, and a target network speed sequence is determined according to the current network speed and behavior data, wherein the target network speed sequence includes the target network speed of each user terminal adapted to the behavior, then a bandwidth constraint condition and a performance constraint condition are set, a network speed prediction model is called, and a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence are determined according to the gradient descent algorithm, so that the difference between the predicted network speed of each network node and the target network speed is within a preset range, wherein the planning bandwidth sequence includes the planning bandwidth of each network node, and the planning performance sequence includes the planning performance corresponding to the planning bandwidth of each network node, finally the online node of the target terminal is converted to the target node, and the bandwidth of each network node is adjusted to the corresponding planning bandwidth according to the planning bandwidth sequence. Through the above method, when the user moves, the online node of the user terminal can be automatically switched according to the signal strength, and the bandwidth of each network node is re-planned, and the network speed of each user network terminal in the FTTR network is kept from fluctuating greatly, improving the user experience, and improving the flexibility and intelligent level of the FTTR network, which can better meet the increasingly changing network demand.

[0082] As a further embodiment of the method, the step of determining the signal strength sequence according to the current position information comprises:

[0083] In step S21, the position information of each network node is obtained, and a distance sequence is determined according to the position information and the current position, wherein the distance sequence includes the distance between the target terminal and each network node.

[0084] It should be noted that in step S21, the precise position information of all network nodes (such as master optical modem, slave optical modem, etc.) is obtained using GPS, Wi-Fi positioning and other technologies, which can be recorded manually through a network management system (NMS) or each node, and then the obtained position information is stored in a database for subsequent query and calculation, and the Euclidean distance formula is used to calculate the distance between the target terminal and each network node.

[0085] In step S22, a signal strength prediction model is used to determine the signal strength sequence based on the distance sequence.

[0086] In the above embodiment, in order to determine the signal strength sequence, the position information of each network node is acquired, and a distance sequence is determined according to the position information and the current position, wherein the distance sequence comprises the distance between the target terminal and each network node, and then the signal strength sequence is determined based on the signal strength prediction model and according to the distance sequence.

[0087] As a further embodiment of the method, the step of determining the target network speed sequence according to the current network speed and the behavior data comprises:

[0088] In step S31, for each user terminal, the target behavior category corresponding to the user terminal and the cumulative number of times corresponding to the target behavior category are determined according to the behavior data.

[0089] It should be noted that in step S31, the system determines the target behavior category (such as video watching, web browsing, etc.) of each user terminal and the corresponding cumulative number of times by analyzing user behavior data (such as online time, application type used, etc.), which usually involves data mining and pattern recognition techniques, and can identify the main use scenarios and needs of users; through this analysis, the system can quantify the user's use behavior, laying the foundation for subsequent network demand analysis. Identifying the behavior patterns of different users helps to more accurately assess their network needs.

[0090] In step S32, the target behavior category is matched in a preset table to obtain the target demand network speed corresponding to the target behavior category.

[0091] The preset table comprises user behavior category data and demand network speed data, and is used to represent the mapping relationship between the user behavior category data and the demand network speed data.

[0092] It should be noted that in step S32, the system uses a preset mapping table to match the identified target behavior category with the corresponding demand network speed, and the preset table contains the relationship between the behavior category data and the required network speed data, which is usually obtained through historical data statistics and experience summary. This matching helps to develop personalized network speed strategies, thereby improving user experience.

[0093] In step S33, the demand network speed sum of the user terminal is calculated according to the demand network speed and the cumulative number of times, and it is determined whether the current network speed is greater than the demand network speed sum. If yes, the current network speed is taken as the target network speed of the user terminal, otherwise the demand network speed sum is taken as the target network speed of the user terminal.

[0094] Specifically, the required network speed sum of the user terminal is calculated according to the required network speed and the cumulative number, and it is judged whether the current network speed is greater than the required network speed sum. If the current network speed is greater than the required network speed sum, the current network speed is taken as the target network speed of the user terminal. If the current network speed is not greater than the required network speed sum, the required network speed sum is taken as the target network speed of the user terminal.

[0095] It should be noted that in step S33, the system calculates the required network speed sum of all target behavior categories and compares it with the current actual network speed. This process may involve mathematical operations and conditional judgments to ensure that the user terminal can obtain the optimal network speed setting. This dynamic adjustment mechanism can ensure that the network speed always meets the user's demand during use.

[0096] In step S34, a target network speed sequence is generated according to the target network speed of each user terminal.

[0097] In the above embodiment, in order to determine the target network speed sequence, for each user terminal, the target behavior category corresponding to the user terminal and the cumulative number corresponding to the target behavior category are determined according to the behavior data, and then the target behavior category is matched in a preset table to obtain the target required network speed corresponding to the target behavior category, wherein the preset table includes user behavior category data and required network speed data, and the preset table is used to represent the mapping relationship between the user behavior category data and the required network speed data. Then, the required network speed sum of the user terminal is calculated according to the required network speed and the cumulative number, and it is judged whether the current network speed is greater than the required network speed sum. If the current network speed is greater than the required network speed sum, the current network speed is taken as the target network speed of the user terminal. If the current network speed is less than the required network speed sum, the required network speed sum is taken as the target network speed of the user terminal. Finally, a target network speed sequence is generated according to the target network speed of each user terminal.

[0098] As a further embodiment of the method, the method for generating a network speed prediction model comprises:

[0099] In step S41, an evaluation parameter set is obtained, wherein the evaluation parameter set includes first historical bandwidth data and first historical performance data corresponding to the first historical bandwidth data.

[0100] In step S42, the Pearson coefficient between each parameter in the evaluation parameter set is calculated, and the mutual exclusivity between each parameter in the evaluation parameter set is evaluated according to the Pearson coefficient to determine a mutually exclusive parameter group.

[0101] It should be noted that in step S42, a program (such as Python) is written to calculate the Pearson coefficient between all pairs of parameters, and a commonly used library is NumPy or Pandas. The results are saved to a matrix or data frame, and it is determined which pairs of parameters are mutually exclusive according to a set threshold.

[0102] Step S43, linearly transforming the mutually exclusive parameter set to obtain corresponding merged parameters.

[0103] Step S44, constructing a model based on a decision tree algorithm and according to the merged parameters and the evaluation parameter set to obtain an initial decision tree model.

[0104] Step S45, training and testing the initial decision tree model according to model training data to obtain the network speed prediction model.

[0105] In the above embodiment, in order to generate the network speed prediction model, the evaluation parameter set is obtained, wherein the evaluation parameter set includes the first historical bandwidth data and the first historical performance data corresponding to the first historical bandwidth data, then the Pearson coefficients between parameters in the evaluation parameter set are calculated, and the mutual exclusivity between parameters in the evaluation parameter set is evaluated according to the Pearson coefficients, the mutually exclusive parameter set is determined, then the mutually exclusive parameter set is linearly transformed to obtain corresponding merged parameters, then a model is constructed based on a decision tree algorithm and according to the merged parameters and the evaluation parameter set to obtain an initial decision tree model, and finally the initial decision tree model is trained and tested according to model training data to obtain the network speed prediction model.

[0106] As a further embodiment of the method, the step of training and testing the initial decision tree model according to model training data to obtain the network speed prediction model comprises:

[0107] Step S51, obtaining model training data, the model training data including second historical bandwidth data, second historical performance data corresponding to the second historical bandwidth data, and historical network speed data, and dividing the model training data into a training set and a test set according to a preset ratio.

[0108] Step S52, setting hyperparameters of the initial decision tree model according to a genetic algorithm, and taking root mean square error (RMSE) and coefficient of determination (R2) as evaluation indexes.

[0109] Step S53, training the initial decision tree model according to the training set to obtain a trained decision tree model.

[0110] Step S54, testing the trained decision tree model according to the test set, and determining whether the errors are all within a preset range according to the evaluation indexes, if yes, taking the trained decision tree model as the network speed prediction model.

[0111] In the above embodiment, in order to realize the training and testing of the initial decision tree model, first, the model training data is obtained, the model training data includes the second historical bandwidth data, the second historical performance data corresponding to the second historical bandwidth data and the historical network speed data, the model training data is divided into a training set and a test set according to a preset proportion, then the hyperparameters of the initial decision tree model are set according to the genetic algorithm, and the root mean square error RMSE and the determination coefficient R2 are used as evaluation indexes, then the initial decision tree model is trained according to the training set, to obtain a trained decision tree model, finally, the trained decision tree model is tested according to the test set, and whether the errors are all within the preset range is judged according to the evaluation indexes, if yes, the trained decision tree model is used as the network speed prediction model.

[0112] As a further embodiment of the method, after the step of testing the trained decision tree model according to the test set and judging whether the errors are all within the preset range according to the evaluation indexes, if yes, the trained decision tree model is used as the network speed prediction model, further comprising:

[0113] Step S61, obtaining target bandwidth data and target performance data.

[0114] The target performance data includes target packet loss rate, target throughput, target connection number and target delay.

[0115] Step S62, inputting the target bandwidth data and the performance data into the network speed prediction model to obtain the corresponding predicted network speed.

[0116] In the above embodiment, in order to realize the prediction of the network speed, first, the target bandwidth data and the target performance data are obtained, wherein the target performance data includes target packet loss rate, target throughput, target connection number and target delay, then the target bandwidth data and the target performance data are input into the network speed prediction model to obtain the corresponding predicted network speed.

[0117] As a further embodiment of the method, the step of determining the planning bandwidth sequence and the planning performance sequence corresponding to the planning bandwidth sequence according to the gradient descent algorithm so that the network speed of each network node is closest to the target network speed, comprises:

[0118] Step S71, obtaining the merging logic of the merging parameters, and defining the search parameter space according to the merging logic, the bandwidth constraint condition and the performance constraint condition.

[0119] It should be noted that in step S71, the merging parameters related to the bandwidth and performance of the network nodes need to be obtained, for example, the traffic distribution between nodes, bandwidth limitations and performance evaluation criteria (such as delay, packet loss rate, etc.) may be considered, and when defining the search parameter space, the parameter space can be simplified according to the merging logic, which reduces noise and risk, and also improves the performance of the model and the accuracy of the optimization results.

[0120] In step S72, the search space is mapped according to the merging parameters and the evaluation parameter set, and the parameter space distance is defined according to the Euclidean distance.

[0121] In step S73, the initial search value and the initial search direction are set, and the initial search is set.

[0122] In step S74, the iteration is performed according to the iteration point and the search direction , wherein, is the (k+1)th iteration point, is the kth iteration point, is the search step size, is the search direction of the kth iteration point, is the search direction of the (k+1)th iteration point, is the update factor of the kth iteration point, is the gradient in the Euclidean space.

[0123] In step S75, the network speed is predicted according to the network speed prediction model, the prediction result is obtained, and it is judged whether the termination condition is met according to the prediction result. If yes, it means that the planning bandwidth of each network node and the planning performance corresponding to the planning bandwidth are searched.

[0124] In step S76, the planning bandwidth sequence is generated according to the planning bandwidth of each network node, and the planning performance sequence is generated according to the planning performance of each network node.

[0125] In the above embodiment, in order to determine the planning bandwidth sequence and the planning performance sequence corresponding to the planning bandwidth sequence, the merging logic of the merging parameters is obtained first, and then the search parameter space is defined according to the merging logic, the bandwidth constraint condition and the performance constraint condition. Then, the search space is mapped according to the merging parameters and the evaluation parameter set, and the parameter space distance is defined according to the Euclidean distance. Then, the initial search value and the initial search direction are set, and the initial search is set. Then, the iteration is performed according to the iteration point and the search direction , wherein, is the (k+1)th iteration point, is the kth iteration point, is the search step size, is the search direction of the kth iteration point, a search direction for the (k+1)th iteration point, an update factor for the kth iteration point, a gradient in the Euclidean space, then the network speed is predicted according to the network speed prediction model, a prediction result is obtained, and it is judged whether the termination condition is met according to the prediction result, if yes, the planning bandwidth of each network node and the planning performance corresponding to the planning bandwidth are represented, finally, a planning bandwidth sequence is generated according to the planning bandwidth of each network node, and a planning performance sequence is generated according to the planning performance of each network node.

[0126] The embodiment of the application further discloses an FTTR network resource planning system.

[0127] Reference Figure 2 An FTTR network resource planning system, comprising:

[0128] A target terminal determination module is configured to monitor current position information of each user terminal in the FTTR network according to a preset frequency, and determine a target terminal according to the current position information, wherein the target terminal is a user terminal whose distance between the current position and the last collected position exceeds a preset distance;

[0129] A target node determination module is configured to determine a signal strength sequence according to the current position information, and determine a target node according to the signal strength sequence, wherein the signal strength sequence comprises signal strengths of the target terminal to each network node, and each network node at least comprises a master optical modem and a slave optical modem;

[0130] A target network speed sequence determination module is configured to acquire current network speeds and behavior data of each user terminal, and determine a target network speed sequence according to the current network speeds and the behavior data, wherein the target network speed sequence comprises target network speeds adapted to behaviors of each user terminal;

[0131] A planning module is configured to set a bandwidth constraint condition and a performance constraint condition, call a network speed prediction model, and determine a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm, so that differences between predicted network speeds of each network node and the target network speed are all within a preset range, wherein the planning bandwidth sequence comprises planning bandwidths of each network node, and the planning performance sequence comprises planning performances corresponding to the planning bandwidths of each network node;

[0132] A network adjustment module is configured to convert an online node of the target terminal into the target node, and adjust bandwidths of each network node to corresponding planning bandwidths according to the planning bandwidth sequence.

[0133] The FTTR network resource planning method of the present application can implement any one of the methods in the FTTR network resource planning system, and the specific working process of the FTTR network resource planning method of the present application can refer to the corresponding process of the FTTR network resource planning system described above.

[0134] The present application also discloses a computer device.

[0135] Reference Figure 3 A computer device, comprising a memory and a processor, the memory storing a computer program capable of running on the processor, and the processor implements any one of the FTTR network resource planning methods described above when executing the computer program.

[0136] The present application also discloses a computer readable storage medium.

[0137] A computer readable storage medium stores a computer program capable of being loaded and executed by a processor to implement any one of the FTTR network resource planning methods described above.

[0138] The computer readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or apparatus; the program code contained on the computer readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any appropriate combination of the above.

[0139] The above are the preferred embodiments of the present application, and are not intended to limit the protection scope of the present application; any feature disclosed in the specification (including the abstract and the drawings) can be replaced by other equivalent or similar features, unless specifically stated otherwise. That is, each feature is only an example of a series of equivalent or similar features, unless specifically stated otherwise.

Claims

1. A method for FTTR network resource planning, characterized in that, The method comprises the following steps: monitoring current position information of each user terminal in the FTTR network according to a preset frequency, and determining a target terminal according to the current position information, wherein the target terminal is a user terminal whose distance between a current position and a last collected position exceeds a preset distance; determining a signal strength sequence according to the current position information, and determining a target node according to the signal strength sequence, wherein the signal strength sequence comprises signal strengths of the target terminal to each network node, and the network node at least comprises a master optical modem and a slave optical modem; obtaining current network speeds and behavior data of the user terminals, and determining a target network speed sequence according to the current network speeds and the behavior data, wherein the target network speed sequence comprises target network speeds of the user terminals that are adapted to behaviors of the user terminals; setting a bandwidth constraint condition and a performance constraint condition, calling a network speed prediction model, and determining a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm, so that a difference between a predicted network speed of the network node and the target network speed is within a preset range, wherein the planning bandwidth sequence comprises planning bandwidths of the network nodes, and the planning performance sequence comprises planning performances corresponding to the planning bandwidths of the network nodes; converting an online node of the target terminal to the target node, and adjusting the bandwidths of the network nodes to the corresponding planning bandwidths according to the planning bandwidth sequence.

2. The FTTR network resource planning method of claim 1, wherein, The step of determining the signal strength sequence according to the current position information comprises: obtaining position information of the network nodes, and determining a distance sequence according to the position information and the current position, wherein the distance sequence comprises distances between the target terminal and the network nodes; determining the signal strength sequence based on a signal strength prediction model and according to the distance sequence.

3. The FTTR network resource planning method of claim 1, wherein, The step of determining the target network speed sequence according to the current network speeds and the behavior data comprises: for each user terminal, determining a target behavior type corresponding to the user terminal and a cumulative number corresponding to the target behavior type according to the behavior data; matching the target behavior type in a preset table to obtain a target demand network speed corresponding to the target behavior type, wherein the preset table comprises user behavior type data and demand network speed data, and the preset table is used to represent a mapping relationship between the user behavior type data and the demand network speed data; calculating a demand network speed sum of the user terminal according to the demand network speed and the cumulative number, and determining whether the current network speed is greater than the demand network speed sum, if yes, taking the current network speed as the target network speed of the user terminal, otherwise, taking the demand network speed sum as the target network speed of the user terminal; generating a target network speed sequence according to the target network speeds of the user terminals.

4. The FTTR network resource planning method of claim 1, wherein, The method for generating the network speed prediction model comprises: obtaining an evaluation parameter set, wherein the evaluation parameter set comprises first historical bandwidth data and first historical performance data corresponding to the first historical bandwidth data; calculate the Pearson coefficients between parameters in the evaluation parameter set, and evaluate the mutual exclusivity between parameters in the evaluation parameter set according to the Pearson coefficients, to determine a mutually exclusive parameter group; perform linear transformation on the mutually exclusive parameter group to obtain corresponding merged parameters; perform model construction based on a decision tree algorithm and according to the merged parameters and the evaluation parameter set, to obtain an initial decision tree model; train and test the initial decision tree model according to model training data, to obtain a network speed prediction model.

5. The FTTR network resource planning method of claim 4, wherein, The step of training and testing the initial decision tree model according to model training data to obtain a network speed prediction model comprises: obtaining model training data, wherein the model training data comprises second historical bandwidth data, second historical performance data corresponding to the second historical bandwidth data, and historical network speed data, and the model training data is divided into a training set and a test set according to a preset ratio; According to the genetic algorithm, the hyperparameters of the initial decision tree model are set, and the root mean square error RMSE and the determination coefficient R 2 as an evaluation index; training the initial decision tree model according to the training set to obtain a trained decision tree model; testing the trained decision tree model according to the test set, and determining whether errors are within a preset range according to the evaluation index, and if so, taking the trained decision tree model as the network speed prediction model.

6. The FTTR network resource planning method of claim 5, wherein, After the step of testing the trained decision tree model according to the test set, and determining whether errors are within a preset range according to the evaluation index, and if so, taking the trained decision tree model as the network speed prediction model, the method further comprises: obtaining target bandwidth data and target performance data, wherein the target performance data comprises a target packet loss rate, a target throughput, a target number of connections, and a target delay; inputting the target bandwidth data and the performance data into the network speed prediction model to obtain corresponding predicted network speeds.

7. The FTTR network resource planning method of claim 4, wherein, The step of determining a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm, so that the network speeds of the network nodes are closest to the target network speeds, comprises: obtaining a merging logic of the merged parameters, and defining a search parameter space according to the merging logic, the bandwidth constraint condition, and the performance constraint condition; performing search space mapping according to the merged parameters and the evaluation parameter set, and defining a parameter space distance according to Euclidean distance; setting an initial search value and an initial search direction, and setting an initial search; According to the iteration point and the search direction performing iterations, wherein, is the k+1 iteration point, is the k iteration point, is the search step length, is the search direction of the k iteration point, is the search direction of the k+1 iteration point, is the update factor of the k iteration point, is the gradient under the Euclidean space; performing network speed prediction according to the network speed prediction model to obtain a prediction result, and determining whether a termination condition is met according to the prediction result, and if so, indicating that the planning bandwidth of the network nodes and the planning performance corresponding to the planning bandwidth are searched; generating a planning bandwidth sequence according to the planning bandwidth of the network nodes, and generating a planning performance sequence according to the planning performance of the network nodes.

8. An FTTR network resource planning system, characterized by, comprises: a target terminal determination module configured to monitor current location information of each user terminal in an FTTR network according to a preset frequency, and determine a target terminal according to the current location information, wherein the target terminal is a user terminal whose distance between a current location and a last collected location exceeds a preset distance. The target node determining module is configured to determine a signal strength sequence according to the current position information, and determine a target node according to the signal strength sequence, wherein the signal strength sequence comprises signal strengths of the target terminal to each network node, and the each network node at least comprises a master optical modem and a slave optical modem; The target network speed sequence determining module is configured to acquire current network speeds and behavior data of the each user terminal, and determine a target network speed sequence according to the current network speeds and the behavior data, wherein the target network speed sequence comprises target network speeds of the each user terminal adapted to the behavior; The planning module is configured to set a bandwidth constraint condition and a performance constraint condition, call a network speed prediction model, and determine a planning bandwidth sequence and a planning performance sequence corresponding to the planning bandwidth sequence according to a gradient descent algorithm, so that differences between predicted network speeds of the each network node and the target network speed are all within a preset range, wherein the planning bandwidth sequence comprises planning bandwidths of the each network node, and the planning performance sequence comprises planning performances corresponding to the planning bandwidths of the each network node; The network adjusting module is configured to convert an online node of the target terminal to the target node, and adjust bandwidths of the each network node to corresponding planning bandwidths according to the planning bandwidth sequence.

9. A computer device, comprising: A computer program is stored in a memory and executable on a processor, and the processor executes the computer program to implement the method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored in a memory and executable on a processor, and the processor executes the computer program to implement the method in any one of claims 1 to 7.

Images