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

Abstract

The application discloses an FTTR network resource scheduling method, system, device and medium, relates to the technical field of network, and the method comprises the following steps: acquiring the transmitting power of each network node in the FTTR network, and determining a signal overlapping area according to the transmitting power; acquiring first position information of each user terminal, and determining whether the user terminal exists in the signal overlapping area according to the first position information, if yes, determining a target terminal and a non-target terminal according to the first position information; acquiring second position information of the network nodes, and determining a first receiving power constraint condition of the non-target terminal and a second receiving power constraint condition of the target terminal according to the first position information and the second position information; calling a receiving power prediction model, and filtering out a group of transmitting powers according to a simulated annealing algorithm. The application has the effect of reducing the interference between wireless signals in the FTTR network.

Description

TECHNICAL FIELD

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

[0002] FTTR (Fiber To The Room) network as a new emerging fiber access technology, aims to provide higher speed and more stable network connection, to meet the growing demand of users on the Internet, FTTR B is more concerned about the network layout inside the building, to ensure that each room has good network coverage and access capability, in modern commercial buildings, hotels and multi-family residences, FTTR B scheme can effectively meet the demand of high-density user groups for network bandwidth and stability, using fiber connection to provide efficient and convenient service for each user. In the FTTR network, the master optical modem and multiple slave optical modems jointly constitute the core of the network, and the transmission power is crucial to signal coverage and user terminal connection quality. Effective power regulation can optimize signal propagation, reduce connection interruption and delay, and thus improve user experience.

[0003] However, FTTR network also faces certain challenges when implementing power regulation. For example, although precise transmission power configuration can improve network performance, in the signal overlapping area, the transmission signals of multiple network nodes may interfere with each other, resulting in reduced wireless signal quality. In addition, due to the distribution and mobility of user terminals, the change of received signals is not always stable, which further aggravates the problem of interference and signal attenuation. These shortcomings make the power regulation scheme need to be continuously optimized in practical application to adapt to complex network environment and guarantee the stability and reliability of signals. SUMMARY

[0004] In order to reduce the interference between wireless signals in FTTR network and improve signal quality, the application provides an FTTR network resource scheduling method, system, device and medium.

[0005] In the first aspect, the application provides an FTTR network resource scheduling method, which adopts the following technical scheme:

[0006] An FTTR network resource scheduling method, comprising:

[0007] obtaining the transmission power of each network node in the FTTR network, and determining the signal overlapping area according to the transmission power, wherein the each network node includes a master optical modem and multiple slave optical modems;

[0008] First location information of each user terminal is obtained, and the presence of the user terminal in the signal overlap area is determined based on the first location information. If so, a target terminal and a non-target terminal are determined based on the first location information, wherein the target terminal is the user terminal in the signal overlap area and the non-target terminal is the user terminal outside the signal overlap area.

[0009] The second location information of each network node is obtained, and the first receiving power constraint condition of the non-target terminal and the second receiving power constraint condition of the target terminal are determined based on the first location information and the second location information.

[0010] The transmit power standard limit of each network node is obtained, the receive power prediction model is called, and a set of transmit power is selected according to the simulated annealing algorithm. The set of transmit power satisfies the transmit power standard limit, and the predicted power corresponding to the set of transmit power satisfies the first receive power constraint and the second receive power constraint.

[0011] The power of each network node is adjusted according to the set of transmission powers to adjust the transmission power of each network node to the power corresponding to the set of transmission powers.

[0012] By adopting the above technical solution, the transmit power of each network node in the FTTR network is first obtained, and the signal overlap area is determined based on the transmit power. Each network node includes a master optical modem and multiple slave optical modems. Then, the first location information of each user terminal is obtained, and it is determined whether a user terminal exists within the signal overlap area based on the first location information. If a user terminal exists within the signal overlap area, a target terminal and a non-target terminal are determined based on the first location information. The target terminal is the user terminal within the signal overlap area, and the non-target terminal is the user terminal outside the signal overlap area. Then, the second location information of each network node is obtained, and the first receive power constraint condition for the non-target terminal and the second receive power constraint condition for the target terminal are determined based on the first and second location information. Finally, the transmit power standard limit of each network node is obtained, and the receive power prediction is invoked. The model uses a simulated annealing algorithm to select a set of transmit powers that meet transmit power standard constraints. The predicted power corresponding to this set of transmit powers also meets the first and second receive power constraints. Finally, the power of each network node is adjusted based on this set of transmit powers to bring its transmit power to the level corresponding to the set of transmit powers. This FTTR network resource scheduling method optimizes signal coverage and reception quality by accurately obtaining the transmit power of network nodes and the location of user terminals. Utilizing a receive power prediction model and a simulated annealing algorithm, this method can flexibly adjust the transmit power of each node, reduce interference between wireless signals, improve the stability and reliability of wireless signals, and effectively avoid resource waste, thereby enhancing the user's network experience and ensuring stable and efficient connection services in different environments.

[0013] Optionally, the step of determining the signal overlap region based on the transmission power includes:

[0014] The signal propagation model is invoked to determine the signal coverage area of ​​each network node based on the transmission power.

[0015] Determine whether the signal coverage areas of each network node overlap; if so, determine the signal overlap area based on the signal coverage areas of each network node.

[0016] By adopting the above technical solution, in order to determine the signal overlap area, the signal propagation model is invoked, the signal coverage area of ​​each network node is determined according to the transmission power, and then it is determined whether the signal coverage areas of each network node overlap. If there is an overlap, the signal overlap area is determined according to the signal coverage area of ​​each network node.

[0017] Optionally, the step of determining the first receive power constraint condition for the non-target terminal based on the first location information and the second location information includes:

[0018] For each of the non-target terminals connected to the same non-target node, first target location information corresponding to each non-target terminal is obtained according to the first location information, and second target location information of the non-target node is obtained according to the second location information, wherein the non-target node is the network node wirelessly connected to the non-target terminal;

[0019] At least one target distance is determined based on the first target location information and the second target location information, and a maximum distance value is determined based on the at least one target distance;

[0020] Based on the transmit power prediction function, and according to the maximum distance, the first minimum receive power corresponding to the same non-target node is determined;

[0021] The corresponding first receive power constraint condition is determined based on the first minimum receive power.

[0022] By adopting the above technical solution, in order to determine the first received power constraint condition of the non-target terminal, for each non-target terminal connected to the same non-target node, the first target location information corresponding to the non-target terminal is obtained according to the first location information, and the second target location information of the non-target node is obtained according to the second location information, wherein the non-target node is a network node wirelessly connected to the non-target terminal. Then, at least one target distance is determined according to the first target location information and the second target location information, and the maximum distance value is determined according to the at least one target distance. Then, based on the transmit power prediction function and the maximum distance value, the first minimum received power corresponding to the non-target node is determined. Finally, the first received power constraint condition corresponding to the non-target terminal is determined according to the first minimum received power.

[0023] Optionally, the step of determining the second receive power constraint condition of the target terminal based on the first location information and the second location information includes:

[0024] Based on the signal overlap area, each corresponding signal overlap node is determined, and based on the second location information, the third target location information corresponding to each signal overlap node is obtained, wherein the signal overlap node is the network node corresponding to the wireless signal in the signal overlap area;

[0025] The fourth target location information corresponding to the target terminal is obtained based on the first location information, and an optional distance set is generated based on the third target location information and the fourth location information;

[0026] For any of the signal overlapping nodes, the signal overlapping node is taken as the target connection node, and non-target connection nodes are determined based on the target connection node, wherein each signal overlapping node is composed of the target connection node and the non-target connection node;

[0027] The first optional distance corresponding to the target connection node is obtained according to the optional distance set, and the second optional distance corresponding to the non-target connection node is obtained according to the optional distance set.

[0028] The second minimum received power corresponding to the target connection node is determined based on the first optional distance, and the maximum received power corresponding to the non-target connection node is determined based on the second optional distance;

[0029] The second receive power constraint condition of the target terminal is determined based on the second minimum receive power and the maximum receive power.

[0030] By adopting the above technical solution, in order to determine the second receiving power constraint of the target terminal, each corresponding signal overlapping node is determined according to the signal overlapping area, and the third target location information corresponding to each signal overlapping node is obtained according to the second location information. The signal overlapping node is the network node corresponding to the wireless signal in the signal overlapping area. Then, the fourth target location information corresponding to the target terminal is obtained according to the first location information, and an optional distance set is generated according to the third target location information and the fourth location information. Then, for any signal overlapping node among the signal overlapping nodes, the signal overlapping node is taken as the target connection node, and non-target connection nodes are determined according to the target connection node. Each signal overlapping node consists of target connection nodes and non-target connection nodes. Then, the first optional distance corresponding to the target connection node is obtained according to the optional distance set, and the second optional distance corresponding to the non-target connection node is obtained according to the optional distance set. Then, the second minimum receiving power corresponding to the target connection node is determined according to the first optional distance, and the maximum receiving power corresponding to the non-target connection node is determined according to the second optional distance. Finally, the second receiving power constraint of the target terminal is determined according to the second minimum receiving power and the maximum receiving power.

[0031] Optionally, the step of selecting a set of transmit powers according to the simulated annealing algorithm, wherein the set of transmit powers satisfies the transmit power standard limit, and the predicted power corresponding to the set of transmit powers satisfies the first receive power constraint and the second receive power constraint, includes:

[0032] In the initial state, the initial temperature T, cooling rate α, and iteration number i are set, and the various transmission power parameters are initialized according to the transmission power standard.

[0033] Annealing is performed for i iterations. After annealing is completed, it is determined whether the first predicted value corresponding to each transmit power parameter in the current state satisfies the first receive power constraint and the second receive power constraint. If so, the corresponding transmit power parameters are taken as a set of transmit power.

[0034] Otherwise, based on the random selection of n parameter points within the transmit power standard limit, for each parameter point, the distance between the second predicted value corresponding to the parameter point and the receive power constraint is calculated, and the shortest distance is determined based on the distance. The parameter points corresponding to the shortest distance are used as a group of transmit power, wherein the receive power constraint consists of the first receive power constraint and the second receive power constraint.

[0035] By adopting the above technical solution, in order to select a set of transmit power, in the initial state, the initial temperature T, cooling rate α, and iteration number i are set. The transmit power parameters are initialized according to the transmit power standard constraints. Then, annealing is performed for i iterations. After annealing, it is determined whether the first predicted value corresponding to each transmit power parameter in the current state satisfies the first and second receive power constraints. If so, the corresponding transmit power parameters are taken as a set of transmit power. Otherwise, n parameter points are randomly selected within the transmit power standard constraints. For each parameter point, the distance between the second predicted value corresponding to the parameter point and the receive power constraint is calculated. The shortest distance is determined based on the distance, and the parameter point corresponding to the shortest distance is taken as a set of transmit power. The receive power constraint consists of the first and second receive power constraints.

[0036] Optionally, the step of generating the received power prediction model includes:

[0037] Acquire model training data and divide the model training data into a training set and a test set according to a preset ratio. The model training data includes historical transmit power data and corresponding historical receive power data.

[0038] The hyperparameters of the initial random forest model are set according to the grid search algorithm, and the root mean square error (RMSE) and the coefficient of determination (R²) are used as evaluation indicators.

[0039] The initial random forest model is trained using the training set to obtain a trained random forest model.

[0040] The trained random forest model is tested according to the test set, and the error is judged according to the evaluation index to determine whether the error is within the preset range. If so, the trained random forest model is used as the received power prediction model.

[0041] By adopting the above technical solution, in order to generate a received power prediction model, model training data is obtained and divided into a training set and a test set according to a preset ratio. The model training data includes historical transmit power data and historical received power data corresponding to the historical transmit power data. Then, the hyperparameters of the initial random forest model are set according to the grid search algorithm, and the root mean square error (RMSE) and coefficient of determination (R²) are used as evaluation indicators. The initial random forest model is then trained on the training set to obtain a trained random forest model. Finally, the trained random forest model is tested on the test set, and the error is judged according to the evaluation indicators to see if it is within the preset range. If the error is within the preset range, the trained random forest model is used as the received power prediction model.

[0042] Optionally, after the step of testing the trained random forest model according to the test set and determining whether the errors are all within a preset range according to the evaluation metric, and if so, using the trained random forest model as the received power prediction model, the method further includes:

[0043] Acquire target transmit power data, wherein the target transmit power data includes the target transmit power corresponding to each network node in the FTTR network;

[0044] The target transmit power data is input into the receive power prediction model to obtain the receive power prediction value corresponding to each network node.

[0045] By adopting the above technical solution, in order to predict the received power of each network node, target transmit power data is obtained. The target transmit power data includes the target transmit power corresponding to each network node in the FTTR network. Then, the target transmit power data is input into the received power prediction model to obtain the predicted received power value corresponding to each network node.

[0046] Secondly, this application also provides an FTTR network resource scheduling system, which adopts the following technical solution:

[0047] An FTTR network resource scheduling system, comprising:

[0048] The signal overlap region determination module is used to obtain the transmit power of each network node in the FTTR network and determine the signal overlap region based on the transmit power, wherein each network node includes a master optical modem and multiple slave optical modems;

[0049] The terminal segmentation module is used to obtain the first location information of each user terminal, and determine whether the user terminal exists in the signal overlap area based on the first location information. If so, it determines the target terminal and the non-target terminal based on the first location information. The target terminal is the user terminal in the signal overlap area, and the non-target terminal is the user terminal outside the signal overlap area.

[0050] The constraint generation module is used to obtain the second location information of each network node, and determine the first received power constraint condition of the non-target terminal and the second received power constraint condition of the target terminal based on the first location information and the second location information.

[0051] The filtering module is used to obtain the standard limit of the transmit power of each network node, call the receive power prediction model, and filter out a set of transmit power according to the simulated annealing algorithm. The set of transmit power satisfies the standard limit of the transmit power, and the predicted power corresponding to the set of transmit power satisfies the first receive power constraint and the second receive power constraint.

[0052] An adjustment module is used to adjust the power of each network node according to the set of transmission powers, so as to adjust the transmission power of each network node to the power corresponding to the set of transmission powers.

[0053] Thirdly, this application also provides a computer device, which adopts the following technical solution:

[0054] A computer device includes a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program to implement the method described in the first aspect.

[0055] Fourthly, this application also provides a computer-readable storage medium, which adopts the following technical solution:

[0056] A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the method described in the first aspect.

[0057] In summary, this application includes at least the following beneficial technical effects: First, the transmit power of each network node in the FTTR network is obtained, and the signal overlap area is determined based on the transmit power. Each network node includes a master optical modem and multiple slave optical modems. Then, the first location information of each user terminal is obtained, and it is determined whether a user terminal exists within the signal overlap area based on the first location information. If a user terminal exists within the signal overlap area, a target terminal and a non-target terminal are determined based on the first location information. The target terminal is the user terminal within the signal overlap area, and the non-target terminal is the user terminal outside the signal overlap area. Next, the second location information of each network node is obtained, and a first receive power constraint condition for the non-target terminal and a second receive power constraint condition for the target terminal are determined based on the first and second location information. Finally, the transmit power standard limit of each network node is obtained, and the receiving power is called... The received power prediction model uses a simulated annealing algorithm to select a set of transmit powers that meet the transmit power standard limits. The predicted power corresponding to this set of transmit powers also meets the first and second received power constraints. Finally, the power of each network node is adjusted based on this set of transmit powers to bring its transmit power to the level corresponding to the set of transmit powers. This FTTR network resource scheduling method optimizes signal coverage and reception quality by accurately obtaining the transmit power of network nodes and the location of user terminals. Utilizing the received power prediction model and the simulated annealing algorithm, this method can flexibly adjust the transmit power of each node, reduce interference between wireless signals, improve the stability and reliability of wireless signals, and effectively avoid resource waste, thereby enhancing the user's network experience and ensuring stable and efficient connection services in different environments. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of the overall process of an embodiment of this application.

[0059] Figure 2 This is a schematic diagram of the system structure of this application.

[0060] Figure 3 This is a structural block diagram of the computer device described in this application. Detailed Implementation

[0061] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-3 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0062] This application discloses an FTTR network resource scheduling method.

[0063] Reference Figure 1An FTTR network resource scheduling method, comprising:

[0064] Step S11: Obtain the transmit power of each network node in the FTTR network, and determine the signal overlap area based on the transmit power.

[0065] Each network node includes a master optical modem and multiple slave optical modems.

[0066] It should be noted that step S11 involves obtaining the transmit power of each network node in the FTTR network. The purpose is to determine the overlapping area of ​​the signals through this information. In this step, the network node includes a master optical modem and multiple slave optical modems. By analyzing the transmit power of each node, the intersection area of ​​the signal coverage of different nodes, i.e. the signal overlap area, can be identified. This provides a basis for subsequent resource scheduling and user terminal positioning.

[0067] Step S12: Obtain the first location information of each user terminal, and determine whether there is a user terminal in the signal overlap area based on the first location information. If so, determine the target terminal and non-target terminal based on the first location information.

[0068] The target terminal is the user terminal within the signal overlap area, and the non-target terminal is the user terminal outside the signal overlap area.

[0069] It should be noted that the main task of step S12 is to obtain the first location information of each user terminal and use this information to determine whether there is a user terminal in the signal overlap area. If there is a user terminal in the signal overlap area, it is marked as a target terminal, while user terminals outside the signal overlap area are marked as non-target terminals. This process helps to clarify the positional relationship of different user terminals and provides important support for subsequent power adjustment and service optimization.

[0070] Step S13: Obtain the second location information of each network node, and determine the first receive power constraint condition for the non-target terminal and the second receive power constraint condition for the target terminal based on the first location information and the second location information.

[0071] It should be noted that the focus of step S13 is to obtain the second location information of each network node. By combining the first location information of the user terminal with the second location information of the network nodes, the first received power constraint condition for non-target terminals and the second received power constraint condition for target terminals can be clearly defined. These received power constraints are an important basis for subsequent power adjustment decisions, helping to ensure that different user terminals obtain the required signal strength at their respective locations, thereby optimizing network performance.

[0072] Step S14: Obtain the standard limit of transmit power for each network node, call the receive power prediction model, and select a set of transmit power according to the simulated annealing algorithm. The set of transmit power satisfies the standard limit of transmit power, and the predicted power corresponding to the set of transmit power satisfies the first receive power constraint and the second receive power constraint.

[0073] It should be noted that the main task of step S14 is to obtain the transmit power standard limits for each network node and analyze them using the receive power prediction model. By applying the simulated annealing algorithm, a set of transmit powers is selected. This set of powers not only meets the set transmit power standard limits but also ensures that the corresponding predicted power satisfies the previously determined first and second receive power constraints. This process provides a scientific basis for subsequent power adjustment, achieving network performance optimization and meeting user needs.

[0074] Step S15: Adjust the power of each network node according to a set of transmission powers to adjust the transmission power of each network node to the power corresponding to the set of transmission powers.

[0075] It should be noted that the core task of step S15 is to adjust the transmission power of each network node according to the previously selected transmission power group. Specifically, the transmission power of each network node is adjusted to the corresponding power value in this transmission power group. This adjustment process aims to ensure that each node in the network can operate at the optimal power level, thereby improving signal quality and network performance, and ensuring that user terminals obtain a more stable and reliable connection.

[0076] In the above implementation, the transmit power of each network node in the FTTR network is first obtained, and the signal overlap area is determined based on the transmit power. Each network node includes a master optical modem and multiple slave optical modems. Then, the first location information of each user terminal is obtained, and it is determined whether a user terminal exists within the signal overlap area based on the first location information. If a user terminal exists within the signal overlap area, a target terminal and a non-target terminal are determined based on the first location information. The target terminal is the user terminal within the signal overlap area, and the non-target terminal is the user terminal outside the signal overlap area. Then, the second location information of each network node is obtained, and the first receive power constraint condition for the non-target terminal and the second receive power constraint condition for the target terminal are determined based on the first and second location information. Finally, the transmit power standard limit of each network node is obtained, and the receive power prediction module is called. The proposed FTTR network resource scheduling method optimizes signal coverage and reception quality by accurately obtaining the transmission power of network nodes and the location of user terminals. Utilizing a reception power prediction model and a simulated annealing algorithm, this method can flexibly adjust the transmission power of each node, reduce interference between wireless signals, improve the stability and reliability of wireless signals, and effectively avoid resource waste, thereby enhancing the user's network experience and ensuring stable and efficient connection services in different environments.

[0077] As a further implementation of the method, the step of determining the signal overlap region based on the transmission power includes:

[0078] Step S21: Invoke the signal propagation model and determine the signal coverage area of ​​each network node based on the transmission power.

[0079] It should be noted that the main task of step S21 is to invoke the signal propagation model to determine the signal coverage area of ​​each network node based on its transmission power. This step accurately calculates and depicts the coverage area of ​​each node, thereby understanding the network's propagation characteristics and signal strength distribution. This information is crucial for optimizing network resource allocation and improving user experience, as it helps identify signal dead zones and overlapping areas, thus supporting subsequent network scheduling and management decisions.

[0080] Step S22: Determine whether the signal coverage areas of each network node overlap. If so, determine the signal overlap area based on the signal coverage areas of each network node.

[0081] In the above implementation, in order to determine the signal overlap area, the signal propagation model is invoked to determine the signal coverage area of ​​each network node based on the transmission power. Then, it is determined whether the signal coverage areas of each network node overlap. If there is an overlap, the signal overlap area is determined based on the signal coverage areas of each network node.

[0082] As a further implementation of the method, the step of determining the first received power constraint condition for the non-target terminal based on the first location information and the second location information includes:

[0083] Step S31: For each non-target terminal connected to the same non-target node, obtain the first target location information corresponding to the non-target terminal according to the first location information, and obtain the second target location information of the non-target node according to the second location information.

[0084] Among them, non-target nodes are network nodes that wirelessly connect to non-target terminals.

[0085] Step S32: Determine at least one target distance based on the first target location information and the second target location information, and determine the maximum distance based on the at least one target distance.

[0086] It should be noted that in step S32, by analyzing multiple first target location information and second target location information, the system automatically calculates at least one target distance. This may involve multiple calculations to reflect different signal attenuation conditions. Then, the maximum distance is identified from these target distances. This maximum distance represents the nearest call or minimum connection distance between the network node and the non-target terminal connected to that network node. This step provides a crucial data foundation for subsequent transmit power calculations, enabling subsequent work to better meet signal coverage requirements.

[0087] Step S33: Based on the received power prediction function, determine the first minimum received power corresponding to the same non-target node according to the maximum distance.

[0088] It should be noted that step S33 uses a transmit power prediction function to calculate the first minimum received power required for the same non-target node. This power value is necessary to ensure that all non-target terminals connected to the same non-target node can receive a valid signal. For each non-target node, there is a maximum distance and a corresponding first minimum received power. In this way, the system can reasonably estimate the received power level of non-target terminals to overcome signal attenuation and propagation loss, thereby ensuring a reliable wireless connection.

[0089] Step S34: Determine the first receiving power constraint condition corresponding to the non-target terminal based on the first minimum received power.

[0090] It is understandable that, for step S34, if the first minimum received power is calculated as x for each non-target terminal connected to the same non-target node, then the received power of each non-target terminal connected to the non-target node should be greater than or equal to x.

[0091] In the above embodiments, in order to determine the first received power constraint condition for non-target terminals, for each non-target terminal connected to the same non-target node, the first target location information corresponding to the non-target terminal is obtained according to the first location information, and the second target location information of the non-target node is obtained according to the second location information, wherein the non-target node is a network node wirelessly connected to the non-target terminal. Then, at least one target distance is determined according to the first target location information and the second target location information, and the maximum distance value is determined according to the at least one target distance. Then, based on the transmit power prediction function and the maximum distance value, the first minimum received power corresponding to the non-target node is determined. Finally, the first received power constraint condition corresponding to the non-target terminal is determined according to the first minimum received power.

[0092] As a further implementation of the method, the step of determining the second receive power constraint condition of the target terminal based on the first location information and the second location information includes:

[0093] Step S41: Determine the corresponding signal overlapping nodes based on the signal overlapping area, and obtain the third target position information corresponding to each signal overlapping node based on the second position information.

[0094] Among them, signal overlap nodes are network nodes corresponding to wireless signals within the signal overlap area.

[0095] It should be noted that step S41 defines corresponding signal overlap nodes based on the signal overlap area. These signal overlap nodes refer to network nodes covered by multiple wireless signals within the signal overlap area. Next, using the second location information, the third target location information corresponding to each signal overlap node is obtained. The key to this step is to identify the sources of frequently overlapping signals in order to further analyze the signal propagation characteristics and interference in the network.

[0096] Step S42: Obtain the fourth target location information corresponding to the target terminal based on the first location information, and generate an optional distance set based on the third target location information and the fourth location information.

[0097] It should be noted that step S42 uses the first location information to obtain the fourth target location information corresponding to the target terminal. The obtained third and fourth target location information will be used to generate an optional distance set. This distance set contains different distance parameters, representing various possible connection methods between the non-target terminal and the target terminal, which is helpful for subsequent network connection and signal strength assessment.

[0098] Step S43: For any signal overlapping node among all signal overlapping nodes, take the signal overlapping node as the target connection node, and determine the non-target connection node based on the target connection node.

[0099] Each signal overlap node consists of a target connection node and a non-target connection node.

[0100] It should be noted that in step S43, any signal overlapping node among the various signal overlapping nodes is designated as the target connection node, and non-target connection nodes are determined accordingly. Signal overlapping nodes, by definition, consist of target and non-target connection nodes. The purpose of this step is to clarify the structural relationships of the terminal connections in order to formulate subsequent signal transmission strategies.

[0101] Step S44: Obtain the first optional distance corresponding to the target connection node according to the optional distance set, and obtain the second optional distance corresponding to the non-target connection node according to the optional distance set.

[0102] It should be noted that in step S44, based on the optional distance set, the system obtains the first optional distance corresponding to the target connection node and the second optional distance corresponding to the non-target connection node. These optional distances will serve as important bases for subsequent signal evaluation and power calculation, providing support for ensuring the stability and effectiveness of the wireless connection.

[0103] Step S45: Determine the second minimum received power corresponding to the target connection node based on the first optional distance, and determine the maximum received power corresponding to the non-target connection node based on the second optional distance.

[0104] It should be noted that step S44 uses the first selectable distance to determine the second minimum received power of the target connection node, and simultaneously determines the maximum received power of the non-target connection node based on the second selectable distance. This process can call the received power prediction function in step S33. By calculating these two received powers, the signal strength requirements at different distances can be evaluated, and the appropriate power setting can be identified to ensure stable wireless communication.

[0105] Step S46: Determine the second receiving power constraint condition of the target terminal based on the second minimum receiving power and the maximum receiving power.

[0106] In the above embodiments, in order to determine the second receive power constraint of the target terminal, each corresponding signal overlapping node is determined according to the signal overlapping area, and the third target location information corresponding to each signal overlapping node is obtained according to the second location information. The signal overlapping node is the network node corresponding to the wireless signal in the signal overlapping area. Then, the fourth target location information corresponding to the target terminal is obtained according to the first location information, and an optional distance set is generated according to the third target location information and the fourth location information. Then, for any signal overlapping node among the signal overlapping nodes, the signal overlapping node is taken as the target connection node, and non-target connection nodes are determined according to the target connection node. Each signal overlapping node consists of a target connection node and a non-target connection node. Then, the first optional distance corresponding to the target connection node is obtained according to the optional distance set, and the second optional distance corresponding to the non-target connection node is obtained according to the optional distance set. Then, the second minimum receive power corresponding to the target connection node is determined according to the first optional distance, and the maximum receive power corresponding to the non-target connection node is determined according to the second optional distance. Finally, the second receive power constraint of the target terminal is determined according to the second minimum receive power and the maximum receive power.

[0107] As a further implementation of the method, the step of selecting a set of transmit powers according to the simulated annealing algorithm, wherein the set of transmit powers meets the transmit power standard limit, and the predicted power corresponding to the set of transmit powers meets the first receive power constraint and the second receive power constraint, includes:

[0108] Step S51: In the initial state, set the initial temperature T, cooling rate α, and iteration number i, and initialize various transmission power parameters according to the transmission power standard limit.

[0109] Step S52: Annealing is performed for i iterations. After annealing, it is determined whether the first predicted value corresponding to each transmit power parameter in the current state satisfies the first receive power constraint and the second receive power constraint. If so, the corresponding transmit power parameters are taken as a set of transmit powers.

[0110] Step S53: Otherwise, randomly select n parameter points within the standard limit of transmit power, calculate the distance between the second predicted value corresponding to each parameter point and the receive power constraint condition, determine the shortest distance based on the distance, and take the parameter points corresponding to the shortest distance as a set of transmit power.

[0111] The received power constraint consists of a first received power constraint and a second received power constraint.

[0112] It should be noted that if the current transmit power parameters fail to meet the receive power constraints, n parameter points must be randomly selected and sampled within the transmit power standard limits. For each parameter point, the distance between the second predicted value generated at that point and the receive power constraints is calculated. These distances reflect the effectiveness of each parameter point, and the system will determine the parameter point corresponding to the shortest distance. Ultimately, the parameter point corresponding to this shortest distance will be selected as a set of transmit power values ​​to ensure that the selected power combination meets the receive power constraints while being as close as possible to the target value. Through this process, the algorithm can effectively filter out the optimal transmit power settings, improving network signal quality and user experience.

[0113] In the above implementation, in order to select a set of transmit power, in the initial state, the initial temperature T, cooling rate α, and iteration number i are set. The transmit power parameters are initialized according to the transmit power standard constraints. Then, annealing is performed for i iterations. After annealing, it is determined whether the first predicted value corresponding to each transmit power parameter in the current state satisfies the first and second receive power constraints. If so, the corresponding transmit power parameters are taken as a set of transmit power. Otherwise, n parameter points are randomly selected within the transmit power standard constraints. For each parameter point, the distance between the second predicted value corresponding to the parameter point and the receive power constraint is calculated. The shortest distance is determined based on the distance, and the parameter point corresponding to the shortest distance is taken as a set of transmit power. The receive power constraint consists of the first and second receive power constraints.

[0114] As a further implementation of the method, the step of generating the power prediction model includes:

[0115] Step S61: Obtain model training data and divide the model training data into a training set and a test set according to a preset ratio. The model training data includes historical transmit power data and historical receive power data corresponding to the historical transmit power data.

[0116] Step S62: Set the hyperparameters of the initial random forest model according to the grid search algorithm, and set the root mean square error (RMSE) and coefficient of determination (R²). 2 As an evaluation indicator.

[0117] Step S63: Train the initial random forest model based on the training set to obtain a trained random forest model.

[0118] Step S64: Test the trained random forest model according to the test set, and determine whether the errors are all within the preset range according to the evaluation index. If so, use the trained random forest model as the received power prediction model.

[0119] In the above implementation, in order to generate the received power prediction model, model training data is acquired and divided into a training set and a test set according to a preset ratio. The model training data includes historical transmit power data and corresponding historical receive power data. Then, the hyperparameters of the initial random forest model are set according to a grid search algorithm, and the root mean square error (RMSE) and coefficient of determination (R²) are set. 2 As an evaluation metric, the initial random forest model is then trained on the training set to obtain a trained random forest model. Finally, the trained random forest model is tested on the test set, and the evaluation metric is used to determine whether the error is within the preset range. If the error is within the preset range, the trained random forest model is used as the received power prediction model.

[0120] As a further implementation of the method, after testing the trained random forest model against a test set and determining whether the errors are all within a preset range based on evaluation metrics, and if so, using the trained random forest model as the received power prediction model, the method further includes:

[0121] Step S71: Obtain target transmit power data.

[0122] The target transmit power data includes the target transmit power of each network node in the FTTR network.

[0123] Step S72: Input the target transmit power data into the receive power prediction model to obtain the receive power prediction value corresponding to each network node.

[0124] In the above implementation, in order to predict the received power of each network node, target transmit power data is obtained, wherein the target transmit power data includes the target transmit power corresponding to each network node in the FTTR network. Then, the target transmit power data is input into the received power prediction model to obtain the received power prediction value corresponding to each network node.

[0125] This application also discloses an FTTR network resource scheduling system.

[0126] refer to Figure 2 An FTTR network resource scheduling system, comprising:

[0127] The signal overlap region determination module is used to obtain the transmit power of each network node in the FTTR network and determine the signal overlap region based on the transmit power. Each network node includes a master optical modem and multiple slave optical modems.

[0128] The terminal segmentation module is used to obtain the first location information of each user terminal and determine whether there is a user terminal in the signal overlap area based on the first location information. If so, the target terminal and the non-target terminal are determined based on the first location information. The target terminal is the user terminal in the signal overlap area and the non-target terminal is the user terminal outside the signal overlap area.

[0129] The constraint generation module is used to obtain the second location information of each network node, and determine the first received power constraint condition of the non-target terminal and the second received power constraint condition of the target terminal based on the first location information and the second location information.

[0130] The filtering module is used to obtain the standard limit of transmit power for each network node, call the receive power prediction model, and filter a set of transmit power according to the simulated annealing algorithm. The set of transmit power meets the standard limit of transmit power, and the predicted power corresponding to the set of transmit power meets the first and second receive power constraints.

[0131] The adjustment module is used to adjust the power of each network node according to a set of transmission power, so as to adjust the transmission power of each network node to the power corresponding to the set of transmission power.

[0132] The FTTR network resource scheduling system of the present invention can implement any of the methods in the FTTR network resource scheduling method, and the specific working process of the FTTR network resource scheduling system of the present invention can refer to the corresponding process in the above-mentioned FTTR network resource scheduling method.

[0133] This application also discloses a computer device.

[0134] refer to Figure 3 A computer device includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement any of the above-described FTTR network resource scheduling methods.

[0135] This application also discloses a computer-readable storage medium.

[0136] A computer-readable storage medium storing a computer program that can be loaded by a processor and executed by any of the above-described FTTR network resource scheduling methods.

[0137] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0138] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for scheduling FTTR network resources, characterized in that, include: The transmit power of each network node in the FTTR network is obtained, and the signal overlap area is determined based on the transmit power, wherein each network node includes a master optical modem and multiple slave optical modems; First location information of each user terminal is obtained, and the presence of the user terminal in the signal overlap area is determined based on the first location information. If so, a target terminal and a non-target terminal are determined based on the first location information, wherein the target terminal is the user terminal in the signal overlap area and the non-target terminal is the user terminal outside the signal overlap area. The second location information of each network node is obtained, and the first receiving power constraint condition of the non-target terminal and the second receiving power constraint condition of the target terminal are determined based on the first location information and the second location information. The transmit power standard limit of each network node is obtained, the receive power prediction model is called, and a set of transmit power is selected according to the simulated annealing algorithm. The set of transmit power satisfies the transmit power standard limit, and the predicted power corresponding to the set of transmit power satisfies the first receive power constraint and the second receive power constraint. The power of each network node is adjusted according to the set of transmission powers to adjust the transmission power of each network node to the power corresponding to the set of transmission powers; The step of determining the first receive power constraint condition for the non-target terminal based on the first location information and the second location information includes: For each of the non-target terminals connected to the same non-target node, first target location information corresponding to each non-target terminal is obtained according to the first location information, and second target location information of the non-target node is obtained according to the second location information, wherein the non-target node is the network node wirelessly connected to the non-target terminal; At least one target distance is determined based on the first target location information and the second target location information, and a maximum distance value is determined based on the at least one target distance; Based on the transmit power prediction function, and according to the maximum distance, the first minimum receive power corresponding to the same non-target node is determined; The corresponding first receive power constraint condition is determined based on the first minimum receive power.

2. The FTTR network resource scheduling method according to claim 1, characterized in that, The step of determining the signal overlap region based on the transmission power includes: The signal propagation model is invoked to determine the signal coverage area of ​​each network node based on the transmission power. Determine whether the signal coverage areas of each network node overlap; if so, determine the signal overlap area based on the signal coverage areas of each network node.

3. The FTTR network resource scheduling method according to claim 1, characterized in that, The step of determining the second receive power constraint condition of the target terminal based on the first location information and the second location information includes: Based on the signal overlap area, each corresponding signal overlap node is determined, and based on the second location information, the third target location information corresponding to each signal overlap node is obtained, wherein the signal overlap node is the network node corresponding to the wireless signal in the signal overlap area; Obtain the fourth target location information corresponding to the target terminal based on the first location information, and generate an optional distance set based on the third target location information and the fourth target location information; For any of the signal overlapping nodes, the signal overlapping node is taken as the target connection node, and non-target connection nodes are determined based on the target connection node, wherein each signal overlapping node is composed of the target connection node and the non-target connection node; The first optional distance corresponding to the target connection node is obtained according to the optional distance set, and the second optional distance corresponding to the non-target connection node is obtained according to the optional distance set. The second minimum received power corresponding to the target connection node is determined based on the first optional distance, and the maximum received power corresponding to the non-target connection node is determined based on the second optional distance; The second receive power constraint condition of the target terminal is determined based on the second minimum receive power and the maximum receive power.

4. The FTTR network resource scheduling method according to claim 1, characterized in that, The step of selecting a set of transmit powers according to the simulated annealing algorithm, wherein the set of transmit powers meets the transmit power standard limit, and the predicted power corresponding to the set of transmit powers meets the first receive power constraint and the second receive power constraint, includes: In the initial state, the initial temperature T, cooling rate α, and iteration number i are set, and the various transmission power parameters are initialized according to the transmission power standard. Annealing is performed for i iterations. After annealing is completed, it is determined whether the first predicted value corresponding to each transmit power parameter in the current state satisfies the first receive power constraint and the second receive power constraint. If so, the corresponding transmit power parameters are taken as a set of transmit power. Otherwise, based on the random selection of n parameter points within the transmit power standard limit, for each parameter point, the distance between the second predicted value corresponding to the parameter point and the receive power constraint is calculated, and the shortest distance is determined based on the distance. The parameter points corresponding to the shortest distance are used as a group of transmit power, wherein the receive power constraint consists of the first receive power constraint and the second receive power constraint.

5. The FTTR network resource scheduling method according to claim 1, characterized in that, The steps for generating the received power prediction model include: Acquire model training data and divide the model training data into a training set and a test set according to a preset ratio. The model training data includes historical transmit power data and corresponding historical receive power data. The hyperparameters of the initial random forest model are set according to the grid search algorithm, and the root mean square error (RMSE) and the coefficient of determination (R²) are used as evaluation indicators. The initial random forest model is trained using the training set to obtain a trained random forest model. The trained random forest model is tested according to the test set, and the error is judged according to the evaluation index to determine whether the error is within the preset range. If so, the trained random forest model is used as the received power prediction model.

6. The FTTR network resource scheduling method according to claim 5, characterized in that, After the steps of testing the trained random forest model against the test set and determining whether the errors are all within a preset range based on the evaluation metric, and if so, using the trained random forest model as the received power prediction model, the method further includes: Acquire target transmit power data, wherein the target transmit power data includes the target transmit power corresponding to each network node in the FTTR network; The target transmit power data is input into the receive power prediction model to obtain the receive power prediction value corresponding to each network node.

7. An FTTR network resource scheduling system, characterized in that, include: The signal overlap region determination module is used to obtain the transmit power of each network node in the FTTR network and determine the signal overlap region based on the transmit power, wherein each network node includes a master optical modem and multiple slave optical modems; The terminal segmentation module is used to obtain the first location information of each user terminal, and determine whether the user terminal exists in the signal overlap area based on the first location information. If so, it determines the target terminal and the non-target terminal based on the first location information. The target terminal is the user terminal in the signal overlap area, and the non-target terminal is the user terminal outside the signal overlap area. The constraint generation module is used to obtain the second location information of each network node, and determine the first received power constraint condition of the non-target terminal and the second received power constraint condition of the target terminal based on the first location information and the second location information. The filtering module is used to obtain the standard limit of the transmit power of each network node, call the receive power prediction model, and filter out a set of transmit power according to the simulated annealing algorithm. The set of transmit power satisfies the standard limit of the transmit power, and the predicted power corresponding to the set of transmit power satisfies the first receive power constraint and the second receive power constraint. An adjustment module is used to adjust the power of each network node according to the set of transmission powers, so as to adjust the transmission power of each network node to the power corresponding to the set of transmission powers; The step of determining the first receive power constraint condition for the non-target terminal based on the first location information and the second location information includes: For each of the non-target terminals connected to the same non-target node, first target location information corresponding to each non-target terminal is obtained according to the first location information, and second target location information of the non-target node is obtained according to the second location information, wherein the non-target node is the network node wirelessly connected to the non-target terminal; At least one target distance is determined based on the first target location information and the second target location information, and a maximum distance value is determined based on the at least one target distance; Based on the transmit power prediction function, and according to the maximum distance, the first minimum receive power corresponding to the same non-target node is determined; The corresponding first receive power constraint condition is determined based on the first minimum receive power.

8. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and execute the method of any one of claims 1 to 6.

Images