Communication bandwidth adjustment method and device, electronic equipment, storage medium and product

Abstract

The invention discloses a communication bandwidth adjustment method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: acquiring an actual bandwidth efficiency value and bandwidth allocation data of a target area at the current moment; determining a first target bandwidth efficiency value corresponding to the current moment from pre-determined historical bandwidth corresponding information; processing the bandwidth allocation data according to a bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current moment; and determining a target efficiency threshold value of the target area at the current moment according to the actual bandwidth efficiency value, the first target bandwidth efficiency value and the target bandwidth allocation data, so as to adjust a bandwidth allocation strategy of the target area according to the target efficiency threshold value. According to the technical scheme, the target efficiency threshold value adapted to the current scene is dynamically determined according to the historical target bandwidth efficiency value, the target bandwidth allocation data and the actual bandwidth efficiency value, and the bandwidth allocation strategy at the current moment is dynamically adjusted according to the target efficiency threshold value.

Description

Technical Field

[0001] This invention relates to the field of vehicle networking technology, and in particular to a communication bandwidth adjustment method, device, electronic device, storage medium, and product. Background Technology

[0002] With the rapid evolution of intelligent transportation and vehicle-to-everything (V2X) technologies, 5G communication networks, with their low latency, high bandwidth, and wide connectivity, have become a key infrastructure supporting core services such as autonomous driving, real-time traffic sharing, and vehicle-road cooperative control. Communication bandwidth allocation, as a core element in ensuring the quality of V2X communication, directly determines service reliability and resource utilization.

[0003] In related technologies, traditional bandwidth allocation typically employs a fixed quota allocation strategy. This static mechanism may have certain limitations, leading to poor bandwidth resource allocation efficiency: during peak hours, intense competition for bandwidth resources results in increased transmission latency and a surge in packet loss rates, while during off-peak hours, bandwidth redundancy leads to resource waste and overall low efficiency. Summary of the Invention

[0004] This invention provides a communication bandwidth adjustment method, apparatus, electronic device, storage medium, and product to achieve the effect of dynamically determining a target performance threshold adapted to the current scenario based on historical target bandwidth performance values, target bandwidth allocation data, and actual bandwidth performance values, and dynamically adjusting the bandwidth allocation strategy at the current moment based on the target performance threshold.

[0005] According to one aspect of the present invention, a communication bandwidth adjustment method is provided, the method comprising:

[0006] Obtain the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current time; wherein, the bandwidth allocation data is used to characterize the communication network operation status of the target area at the current time;

[0007] Based on the current time, a first target bandwidth efficiency value corresponding to the current time is determined from pre-determined historical bandwidth correspondence information; wherein, the historical bandwidth correspondence information is determined based on a pre-trained target efficiency value determination model and historical bandwidth usage data within the target area; the historical bandwidth correspondence information is used to characterize the correspondence between historical times and historical target bandwidth efficiency values;

[0008] The bandwidth allocation data is processed according to a preset bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current time; wherein, the target bandwidth allocation data includes a second target bandwidth performance value and a target bandwidth allocation weight;

[0009] Based on the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, a target performance threshold corresponding to the target region at the current time is determined, so as to adjust the bandwidth allocation strategy of the target region according to the target performance threshold.

[0010] According to another aspect of the present invention, a communication bandwidth adjustment device is provided, the device comprising:

[0011] The data acquisition module is used to acquire the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current time; wherein, the bandwidth allocation data is used to characterize the communication network operation status of the target area at the current time.

[0012] The first bandwidth data determination module is used to determine a first target bandwidth efficiency value corresponding to the current time from pre-determined historical bandwidth correspondence information based on the current time; wherein, the historical bandwidth correspondence information is determined based on a pre-trained target efficiency value determination model and historical bandwidth usage data within the target area; the historical bandwidth correspondence information is used to characterize the correspondence between historical times and historical target bandwidth efficiency values;

[0013] The second bandwidth data determination module is used to process the bandwidth allocation data according to a preset bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current time; wherein, the target bandwidth allocation data includes a second target bandwidth performance value and a target bandwidth allocation weight;

[0014] The performance threshold determination module is used to determine the target performance threshold corresponding to the target region at the current time based on the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, so as to adjust the bandwidth allocation strategy of the target region according to the target performance threshold.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the communication bandwidth adjustment method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the communication bandwidth adjustment method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the communication bandwidth adjustment method described in any embodiment of the present invention.

[0021] The technical solution of this invention obtains the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current moment. The bandwidth allocation data is used to characterize the communication network operation status of the target area at the current moment, capturing the real effect of the current bandwidth usage and the communication network operation status (including resource constraints, service requirements, etc.) in real time. This provides accurate input for the subsequent generation of target bandwidth allocation data by the slime mold algorithm, dynamic determination of the target efficiency threshold, and precise adjustment of the bandwidth allocation strategy, ensuring that bandwidth optimization fits the current network scenario. Furthermore, by determining the first target bandwidth efficiency value corresponding to the current moment from pre-determined historical bandwidth information, and leveraging the historical optimal bandwidth efficiency pattern of the target area, an accurate historical reference benchmark is provided for the current moment, directly supporting the dynamic calculation of the target efficiency threshold and improving the targeting and rationality of subsequent bandwidth allocation strategy adjustments. Furthermore, by processing the bandwidth allocation data according to a preset bandwidth allocation algorithm, target bandwidth allocation data corresponding to the current moment is obtained, providing an objective theoretical benchmark for subsequent target efficiency threshold calculation and precise adjustment of the bandwidth strategy, ensuring the efficiency and adaptability of bandwidth allocation. Furthermore, based on the actual bandwidth efficiency value, the first target bandwidth efficiency value, and the target bandwidth allocation data, a target efficiency threshold corresponding to the target area at the current moment is determined. The bandwidth allocation strategy for the target area is then adjusted according to this target efficiency threshold. By integrating the current actual bandwidth efficiency, historical best references, and theoretically optimal allocation schemes, a precise target efficiency threshold adapted to the current scenario is determined, providing a clear basis for bandwidth allocation strategy adjustments and achieving dynamic optimization and highly adaptable scheduling of bandwidth resources. The technical solution of this invention addresses the limitations of bandwidth resource allocation strategies in related technologies, which lead to poor bandwidth resource allocation effects. It achieves the effect of dynamically determining a target efficiency threshold adapted to the current scenario based on historical target bandwidth efficiency values, target bandwidth allocation data, and actual bandwidth efficiency values, and dynamically adjusting the bandwidth allocation strategy at the current moment based on the target efficiency threshold. This achieves precise and dynamic adjustment of the bandwidth allocation strategy, improves bandwidth resource utilization and network node load balancing, enhances the efficiency of dynamic bandwidth resource allocation, significantly optimizes the allocation effect of bandwidth resources in the target area, and adapts to the complex needs of dynamic communication scenarios such as vehicle-to-everything (V2X) communication.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a communication bandwidth adjustment method provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a communication bandwidth adjustment method provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of a communication bandwidth adjustment device according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the communication bandwidth adjustment method of this invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a communication bandwidth adjustment method provided in Embodiment 1 of the present invention. This embodiment is applicable to the allocation of bandwidth resources in a target area. The method can be executed by a communication bandwidth adjustment device, which can be implemented in hardware and / or software, and can be configured in a terminal and / or server. Figure 1 As shown, the method includes:

[0032] S110. Obtain the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current time.

[0033] With the continuous enhancement of network technology, the promotion and application of edge computing have provided favorable conditions for the implementation of vehicle-to-everything (V2X) technology, promoting the multi-scenario application of autonomous driving technology based on efficient collaboration between vehicles, roads, networks, and the cloud. Currently, to achieve agile execution of V2X services, independent, dedicated network bandwidth with specific performance guarantees has been provided for different V2X applications. In practical applications, multiple application scenarios often arise, and the network resource requirements of V2X services may change dynamically. When it is found that the utilization rate of a certain network bandwidth is too high or too low, or when business needs change (such as the difference in network standards between the autonomous driving testing phase and the actual operation phase), the bandwidth parameters of the network bandwidth allocation can be adjusted in a timely and flexible manner to adapt to the dynamic needs of the business.

[0034] The target area can be understood as a specific region with clearly defined geographical boundaries or network coverage. The target area can be used to define the spatial scope of bandwidth data collection, optimization, and bandwidth allocation strategy execution, avoiding cross-regional network status interference and ensuring targeted bandwidth allocation. Optionally, the target area may include a city, a district / county, a section of main roads in a city, or the vehicle-to-everything (V2X) communication area covered by network base stations. The current time can refer to the real-time point in time at which the bandwidth allocation strategy is executed. The current time can serve as a time anchor for real-time data collection, historical data matching, and theoretical data generation, ensuring consistency of all related data in the time dimension and providing a unified benchmark for subsequent performance threshold calculations. Actual bandwidth usage data refers to the actual bandwidth consumption and performance quantification data of the target area at the current time, which is the core data reflecting the current bandwidth usage status of the target area. Actual bandwidth usage data can include the current time and the corresponding actual bandwidth performance value. The actual bandwidth performance value can refer to a quantitative indicator of the actual bandwidth resource utilization effect within the target area at the current time. The actual bandwidth performance value can be used to reflect the effectiveness of the current bandwidth allocation. The quantitative indicators of actual bandwidth performance can include at least one of the following: bandwidth utilization; transmission latency; packet loss rate; and a performance score obtained through weighted calculation. Actual bandwidth performance can be used to quantify the quality of current bandwidth usage and is a direct basis for determining whether bandwidth allocation strategies need to be adjusted.

[0035] Bandwidth allocation data refers to various quantitative data representing the current operational status of the communication network in the target area, serving as fundamental input data reflecting network resource constraints, service demands, and hardware load. Bandwidth allocation data can include at least one of the following: resource constraint data (including at least one of the following: available bandwidth limit, maximum forwarding bandwidth of network nodes, and link transmission bandwidth limit); load status data (including at least one of the following: total number of access terminals, concurrent data for each service, and real-time load rate of network nodes); service-related data (including at least one of the following: currently running service type (e.g., autonomous driving, navigation updates, video calls), service priority weight, and minimum bandwidth requirements for each service); and link quality data (including at least one of the following: real-time transmission delay, jitter, and packet loss rate). Bandwidth allocation data can be used to characterize the current operational status of the communication network in the target area. The operational status of the communication network can refer to the overall operational status of the communication network in the target area at the current time, including resource utilization, load pressure, service distribution, and link quality. By collecting bandwidth allocation data, the network operational status can be indirectly understood, providing a decision-making basis for bandwidth allocation algorithms.

[0036] In this embodiment, when determining whether the bandwidth allocation strategy for the target area meets the bandwidth allocation requirements at the current moment, the actual bandwidth usage data and bandwidth allocation data of the target area at the current moment can be obtained. Furthermore, based on the obtained actual bandwidth usage data and bandwidth allocation data, it can be determined whether the bandwidth allocation strategy corresponding to the target area at the current moment is the optimal bandwidth allocation strategy.

[0037] S120. Determine the first target bandwidth performance value corresponding to the current time from the pre-determined historical bandwidth information based on the current time.

[0038] Historical bandwidth correspondence information refers to a structured mapping dataset obtained by training and fitting a target performance value determination model with historical bandwidth usage data of a target region. This dataset can be used to characterize the correspondence between historical moments and historical target bandwidth performance values. In other words, historical bandwidth correspondence information is used to characterize the correspondence between historical moments and historical target bandwidth performance values. Historical bandwidth correspondence information includes multiple historical moments and their corresponding historical target bandwidth performance values. Historical target bandwidth performance values ​​can refer to the empirically optimal bandwidth performance value corresponding to a historical moment. This empirically optimal bandwidth performance value can be obtained by training and fitting a target performance value determination model with historical bandwidth usage data of the target region. Historical bandwidth correspondence information can be determined based on a pre-trained target performance value determination model and historical bandwidth usage data within the target region. That is, historical bandwidth usage data within the target region can be provided to the target performance value determination model to obtain historical bandwidth correspondence information.

[0039] The first target bandwidth efficiency value can refer to the optimal bandwidth efficiency value at the current moment, determined based on historical bandwidth information. Alternatively, it can refer to the empirically optimal bandwidth efficiency value corresponding to a historical moment similar to the current moment, retrieved from pre-determined historical bandwidth information. In other words, the first target bandwidth efficiency value can be the historically empirically optimal bandwidth efficiency value corresponding to the current moment, representing the historically optimal efficiency level achievable in the current scenario, rather than the actual bandwidth efficiency value at the current moment. Optionally, the quantification form of the first target bandwidth efficiency value includes at least one of the following: optimal bandwidth utilization; minimum transmission latency; and a performance score obtained through weighted calculation.

[0040] The target performance value determination model can refer to a pre-trained neural network model capable of determining the optimal bandwidth performance value at a corresponding historical moment based on historical bandwidth usage data. This model can be used to extract patterns between time and the optimal bandwidth performance value from massive amounts of historical data. The target performance value determination model can be a neural network model with any model structure. Optionally, the model structure can be a BP neural network model, a deep learning fitting model, etc. The target performance value determination model can be trained on a machine learning model based on historical bandwidth usage data within a target region. In this embodiment, the target performance value determination model can fit historical bandwidth usage data, remove outliers and redundant information, and output the optimal bandwidth performance value (i.e., the historical target bandwidth performance value) for each historical moment, thus forming structured historical bandwidth correspondence information.

[0041] In this embodiment, multiple sets of historical bandwidth usage data within the target area can be acquired. Further, the acquired sets of historical bandwidth usage data can be used as training data to train a machine learning model, and the trained machine learning model can be used as the target performance value determination model. Further, multiple sets of first target bandwidth data can be determined based on the pre-trained target performance value determination model and the multiple sets of historical bandwidth usage data, and historical bandwidth corresponding information can be determined based on the multiple sets of first target bandwidth data. Further, the first target bandwidth performance value corresponding to the current time can be determined from the historical bandwidth corresponding information based on the current time.

[0042] Optionally, the first target bandwidth performance value corresponding to the current time is determined from the predetermined historical bandwidth correspondence information based on the current time, including: determining the historical time associated with the current time from the predetermined historical bandwidth correspondence information, and determining the first target bandwidth performance value corresponding to the current time based on the historical target bandwidth performance value corresponding to the determined historical time.

[0043] Among them, the historical moment associated with the current moment can refer to the historical time point that is similar to the current moment and retrieved from the historical bandwidth information. Optionally, the historical moments associated with the current moment include at least one of the following: If the acquisition step size (including 1 second, 2 seconds, 3 seconds, or 5 seconds, etc.) of the historical moment is consistent with the current moment, and the similarity between the corresponding scene features and the scene features of the current moment meets a preset threshold, then the historical moment is regarded as the historical moment associated with the current moment; If the acquisition step size of the historical moment is inconsistent with the current moment, then among the multiple historical moments whose time difference with the current moment is within a preset time difference threshold (e.g., the current moment is 08:30:00 on June 29, the preset time difference threshold is 10 seconds, and the multiple historical moments within the preset time difference threshold are 08:29:55 on June 28 and 08:30:05 on June 28), the historical moment whose scene features meet the preset threshold is regarded as the historical moment associated with the current moment. It is understandable that scenario characteristics refer to key environmental and operational parameters that directly affect bandwidth demand, bandwidth allocation strategies, and bandwidth efficiency. Optionally, scenario characteristics include at least one of the following: number of access terminals (e.g., 1000 vehicles accessing the network at the current time (08:30:00 on June 29th), and 980 vehicles accessing the network at a historical time (08:30:00 on June 28th), with a difference of ≤2%, meeting a preset threshold); terminal type distribution; terminal density; service type composition; service priority weight; total available bandwidth limit; communication node load status; environmental interference factors.

[0044] In one embodiment, if the current acquisition step size is consistent with the historical acquisition step size, a historical moment consistent with the current moment can be determined from pre-determined historical bandwidth correspondence information, and it can be determined whether the similarity between the scene features of that historical moment and the scene features of the current moment meets a preset threshold. Further, if it is determined that the scene features of the current moment meet the preset threshold, that historical moment can be used as the historical moment associated with the current moment. Subsequently, the historical target bandwidth performance value corresponding to that historical moment stored in the historical bandwidth correspondence information can be used as the first target bandwidth performance value corresponding to the current moment.

[0045] It should be noted that if the similarity between the scene features at the determined historical moment and the scene features at the current moment does not meet the preset threshold, other historical bandwidth information can be used to determine the first target bandwidth efficiency value corresponding to the current moment.

[0046] In one embodiment, when the acquisition step size at the current moment is inconsistent with the acquisition step size at historical moments, multiple historical moments whose time difference with the current moment is within a preset time difference threshold can be determined from the pre-determined historical bandwidth correspondence information. Further, the similarity between the scene features of each historical moment and the scene features of the current moment can be determined, and the historical moments whose similarity meets the preset threshold are taken as the historical moments associated with the current moment. Further, when there is only one historical moment associated with the current moment, the historical target bandwidth efficiency value corresponding to that historical moment stored in the historical bandwidth correspondence information can be used as the first target bandwidth efficiency value corresponding to the current moment. When there are multiple historical moments associated with the current moment, the historical moment corresponding to the highest similarity value can be determined, and the historical target bandwidth efficiency value corresponding to that historical moment can be used as the first target bandwidth efficiency value corresponding to the current moment.

[0047] S130. Process the bandwidth allocation data according to the preset bandwidth allocation algorithm to obtain the target bandwidth allocation data corresponding to the current time.

[0048] The preset bandwidth allocation algorithm can be a pre-defined bandwidth allocation optimization algorithm with global optimization capability under real-time constraints. Optionally, the preset bandwidth allocation algorithm includes at least one heuristic algorithm such as slime mold foraging algorithm, genetic algorithm, and particle swarm optimization algorithm. Target bandwidth allocation data can refer to the theoretically optimal bandwidth allocation data scheme obtained by globally optimizing the bandwidth allocation data at the current moment through the preset bandwidth allocation algorithm; it is a structured carrier of the theoretically optimal state. Target bandwidth allocation data includes a second target bandwidth efficiency value and target bandwidth allocation weights. The second target bandwidth efficiency value can refer to the theoretical bandwidth efficiency value corresponding to the theoretically optimal scheme at the current moment, contained in the target bandwidth allocation data. The second target bandwidth efficiency value can be the theoretically optimal bandwidth utilization effect that can be achieved at the current moment under the premise of full resource utilization, satisfied business needs, and no bottleneck constraints. The unit of the second target bandwidth efficiency value is consistent with the actual bandwidth efficiency value and the first target bandwidth efficiency value; that is, the second target bandwidth efficiency value can include at least one of the following: optimal bandwidth utilization rate; lowest transmission delay; efficiency score obtained through weighted calculation. The target bandwidth allocation weight refers to the resource allocation ratio coefficient corresponding to the theoretically optimal solution at the current moment, contained in the target bandwidth allocation data. It is the core quantitative representation of the theoretically optimal allocation strategy. The target bandwidth allocation weight can be used to clarify how bandwidth resources should be allocated under the theoretically optimal solution, directly guiding the direction of bandwidth adjustment. The quantitative form of the target bandwidth allocation weight can be a weight value or percentage in the range [0,1]. The target bandwidth allocation weight can include, but is not limited to, the bandwidth proportion of each service (e.g., 40% for autonomous driving services and 60% for non-real-time services), the traffic distribution weight of each communication node (e.g., 60% for UPF1 and 40% for UPF2), and the bandwidth quota proportion of each terminal type.

[0049] Optionally, the bandwidth allocation data can be processed according to a preset bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current time, including: processing the bandwidth allocation data according to a slime mold foraging algorithm to obtain target bandwidth allocation data corresponding to the current time.

[0050] In one embodiment, the bandwidth allocation data can be normalized to obtain normalized bandwidth allocation data with the dimension [number of services + number of network nodes × constraint dimension]. Further, an initial population can be randomly generated based on the normalized bandwidth allocation data and pre-determined population initialization parameters. This initial population includes multiple slime mold individuals (i.e., candidate bandwidth allocation schemes, including allocation weights corresponding to each service and each network node). Further, for each slime mold individual, a fitness value is determined according to a preset fitness function. Based on the fitness values ​​of the multiple slime mold individuals, the optimal and worst slime mold individuals are determined. Further, for each slime mold individual, the weight vector corresponding to that slime mold individual can be adjusted based on its fitness value, the fitness value of the optimal slime mold individual, and the fitness value of the worst slime mold individual to update the slime mold individual. Further, the fitness value of each updated slime mold individual is calculated, and the slime mold individual that satisfies all constraints and has the highest fitness is selected as the optimal solution for the current iteration. Furthermore, if the difference between the fitness value corresponding to the current optimal solution and the fitness value corresponding to the previous optimal solution is less than a preset threshold, it indicates convergence, and the iteration can be terminated early (to reduce time consumption); otherwise, the next iteration begins. Further, after the iteration ends, the optimal slime mold individual in the population can be used as the target slime mold individual, and business constraint verification, network node constraint verification, and scenario adaptation verification can be performed on the target slime mold individual. If the verification fails, the weight vector of the target slime mold individual is adjusted according to the constraint requirements, and the fitness value is recalculated; if the verification passes, the target slime mold individual and its corresponding fitness value can be transformed into target bandwidth allocation data: the weight vector corresponding to the target slime mold individual is used as the target bandwidth allocation weight, and the fitness value corresponding to the target slime mold individual is mapped inversely to the actual performance index to obtain the second target bandwidth performance value.

[0051] S140. Based on the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, determine the target performance threshold corresponding to the target area at the current time, and adjust the bandwidth allocation strategy of the target area according to the target performance threshold.

[0052] The target performance threshold refers to a dynamic baseline value for bandwidth allocation at the current moment, obtained through quantitative fusion of actual bandwidth performance, a first target bandwidth performance, and target bandwidth allocation data. This target performance threshold can be dynamically adjusted based on the current network status, historical optimality, and theoretical optimality, rather than being a fixed value, thus combining empirical feasibility, theoretical optimality, and real-time adaptability. The target performance value serves as the core decision-making basis for adjusting bandwidth allocation strategies. When the actual bandwidth performance value falls within this target performance threshold, it indicates that the current bandwidth allocation strategy is effective; when the actual bandwidth performance value does not fall within this target performance threshold, it indicates that the current bandwidth allocation strategy is ineffective and needs adjustment (such as optimizing according to target bandwidth allocation weights, increasing bandwidth for high-priority services, etc.). The bandwidth allocation strategy can refer to the specific implementation plan determined based on the target performance threshold, used to adjust the allocation of bandwidth resources in the target area (such as adjusting bandwidth quotas for each service, traffic distribution ratios of network nodes, and bandwidth priorities of access terminals, etc.). The bandwidth allocation strategy can ensure that the adjusted bandwidth allocation strategy can make the actual bandwidth performance value within the target performance threshold, so as to meet business needs (such as low latency and high reliability) and maximize bandwidth utilization while avoiding congestion or redundancy.

[0053] In this embodiment, after obtaining the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data corresponding to the current time, the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data can be processed according to a preset performance threshold determination method to obtain the target performance threshold corresponding to the target region at the current time. The performance threshold determination method may include at least one of the following: deviation correction combined with Euclidean distance; weighted averaging.

[0054] Optionally, based on the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, the target performance threshold corresponding to the target area at the current time is determined, including: determining a first distance between the actual bandwidth performance value and the first target bandwidth performance value; and determining a second distance between the actual bandwidth performance value and the target bandwidth allocation data; and determining the target performance threshold corresponding to the target area at the current time based on the first distance, the second distance, the first target bandwidth performance value, and the second target bandwidth performance value.

[0055] The first distance refers to the quantitative deviation between the actual bandwidth efficiency value and the first target bandwidth efficiency value, used to measure the difference between the current real-time state and the optimal state of similar historical scenarios. Generally, the smaller the first distance, the closer the current real-time state is to the historical optimal state, and the higher the reference value of the historical experience; conversely, the further the current actual bandwidth efficiency value is from the historical optimal state, the weaker the fit between the historical experience and the current actual bandwidth efficiency value. The first distance can be determined by at least one of the following: two-dimensional Euclidean distance; Manhattan distance; Chebyshev distance; cosine similarity; Pearson correlation coefficient. The second distance refers to the quantitative deviation between the actual bandwidth efficiency value and the target bandwidth allocation data, used to measure the difference between the current real-time state and the theoretical optimal state. Generally, the smaller the second distance, the closer the current real-time state is to the theoretical optimal state, and the stronger the feasibility of the target bandwidth allocation data; conversely, the further the current real-time state is from the theoretical optimal state, the weaker the feasibility of the target bandwidth allocation data. The second distance can be determined by at least one of the following: two-dimensional Euclidean distance; Manhattan distance; Chebyshev distance; cosine similarity; Pearson correlation coefficient.

[0056] In one embodiment, a historical time corresponding to a first target bandwidth performance value can be determined, and the square of the difference between the historical time and the current time can be determined as a first value; and the square of the difference between the first target bandwidth performance value and the actual bandwidth performance value can be determined as a second value. Further, the first and second values ​​can be added to obtain a third value, and the square root of the third value can be taken to obtain a first distance between the actual bandwidth performance value and the first target bandwidth performance value. Additionally, the current time and the target allocation weight can be normalized to obtain normalized current time and target allocation weight. Then, the square of the difference between the normalized current time and the normalized target allocation weight can be determined as a fourth value; and the square of the difference between the second target bandwidth performance value and the actual bandwidth performance value can be determined as a fifth value. Further, the fourth and fifth values ​​can be added to obtain a sixth value, and the square root of the sixth value can be taken to obtain a second distance between the actual bandwidth performance value and the target bandwidth allocation data. Furthermore, the first distance and the second distance can be added together to obtain a distance sum. The ratio between the first distance and the distance sum can be determined to obtain a first distance ratio. The product of the first distance ratio and the first target bandwidth performance value can be determined to obtain a seventh value. Similarly, the ratio between the second distance and the distance sum can be determined to obtain a second distance ratio. The product of the second distance ratio and the second target bandwidth performance value can be determined to obtain an eighth value. Finally, the seventh and eighth values ​​can be added together to obtain the target performance threshold corresponding to the target region at the current time.

[0057] For example, suppose the actual bandwidth efficiency at the current moment is The first target bandwidth efficiency value is The target bandwidth allocation data is The target performance threshold can be determined using the following formula:

[0058] The first distance can be determined using the following formula:

[0059]

[0060] in, Indicates the first distance; This represents the historical moment corresponding to the first target bandwidth performance value; This represents the first target bandwidth performance value; Indicates the current moment; This represents the actual bandwidth performance value.

[0061] The second distance can be determined using the following formula:

[0062]

[0063] in, Indicates the second distance; This represents the normalized target allocation weights; This represents the second target bandwidth efficiency value.

[0064] The target performance threshold can be determined using the following formula:

[0065]

[0066] in, This represents the target performance threshold.

[0067] In this embodiment, after obtaining the target performance threshold corresponding to the target region at the current time, the target performance threshold can be added to a preset tolerance to obtain the upper limit of the performance threshold, and the target performance threshold can be subtracted from the preset tolerance to obtain the lower limit of the performance threshold. A performance threshold range is then constructed based on the upper and lower limits. Furthermore, the actual bandwidth performance value can be compared with the performance threshold range. Further, if the actual bandwidth performance value is less than the lower limit of the performance threshold range, it indicates that the bandwidth resource allocation is uneven and the performance is insufficient at the current time. In this case, the first strategy adjustment scheme can be used to adjust the bandwidth allocation strategy at the current time. If the actual bandwidth performance value is within the performance threshold range, it indicates that the bandwidth allocation strategy at the current time is effective and no adjustment is needed. If the actual bandwidth performance value is greater than the upper limit of the performance threshold range, it indicates that the bandwidth resources are wasted and there is performance redundancy at the current time. In this case, the second strategy adjustment scheme can be used to adjust the bandwidth allocation strategy at the current time.

[0068] Optionally, the first strategy adjustment scheme includes at least one of the following: prioritizing the increase of bandwidth quota for high-priority services (such as autonomous driving); adjusting the traffic allocation ratio according to the target bandwidth allocation weight based on the real-time load rate of network nodes; applying for temporary bandwidth resources (such as expanding from 10Gbps to 12Gbps); and activating backup network nodes.

[0069] Optionally, the second strategy adjustment scheme includes at least one of the following: reducing the bandwidth quota for low-priority services, allocating redundant bandwidth to high-priority services, or reserving it as backup bandwidth; triggering elastic scaling down to release redundant bandwidth resources (such as scaling down from 10Gbps to 8Gbps).

[0070] The technical solution of this invention obtains the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current moment. The bandwidth allocation data is used to characterize the communication network operation status of the target area at the current moment, capturing the real effect of the current bandwidth usage and the communication network operation status (including resource constraints, service requirements, etc.) in real time. This provides accurate input for the subsequent generation of target bandwidth allocation data by the slime mold algorithm, dynamic determination of the target efficiency threshold, and precise adjustment of the bandwidth allocation strategy, ensuring that bandwidth optimization fits the current network scenario. Furthermore, by determining the first target bandwidth efficiency value corresponding to the current moment from pre-determined historical bandwidth information, and leveraging the historical optimal bandwidth efficiency pattern of the target area, an accurate historical reference benchmark is provided for the current moment, directly supporting the dynamic calculation of the target efficiency threshold and improving the targeting and rationality of subsequent bandwidth allocation strategy adjustments. Furthermore, by processing the bandwidth allocation data according to a preset bandwidth allocation algorithm, target bandwidth allocation data corresponding to the current moment is obtained, providing an objective theoretical benchmark for subsequent target efficiency threshold calculation and precise adjustment of the bandwidth strategy, ensuring the efficiency and adaptability of bandwidth allocation. Furthermore, based on the actual bandwidth efficiency value, the first target bandwidth efficiency value, and the target bandwidth allocation data, a target efficiency threshold corresponding to the target area at the current moment is determined. The bandwidth allocation strategy for the target area is then adjusted according to this target efficiency threshold. By integrating the current actual bandwidth efficiency, historical best references, and theoretically optimal allocation schemes, a precise target efficiency threshold adapted to the current scenario is determined, providing a clear basis for bandwidth allocation strategy adjustments and achieving dynamic optimization and highly adaptable scheduling of bandwidth resources. The technical solution of this invention addresses the limitations of bandwidth resource allocation strategies in related technologies, which lead to poor bandwidth resource allocation effects. It achieves the effect of dynamically determining a target efficiency threshold adapted to the current scenario based on historical target bandwidth efficiency values, target bandwidth allocation data, and actual bandwidth efficiency values, and dynamically adjusting the bandwidth allocation strategy at the current moment based on the target efficiency threshold. This achieves precise and dynamic adjustment of the bandwidth allocation strategy, improves bandwidth resource utilization and network node load balancing, enhances the efficiency of dynamic bandwidth resource allocation, significantly optimizes the allocation effect of bandwidth resources in the target area, and adapts to the complex needs of dynamic communication scenarios such as vehicle-to-everything (V2X) communication.

[0071] Example 2

[0072] Figure 2 This is a flowchart of a communication bandwidth adjustment method provided in Embodiment 2 of the present invention. Based on the foregoing embodiments, historical bandwidth correspondence information can be constructed before applying it. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or similar to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes:

[0073] S210. Obtain multiple sets of historical bandwidth usage data for the target area within a historical time period; wherein, the historical bandwidth usage data includes the historical time and the corresponding historical bandwidth efficiency value at the historical time.

[0074] Historical time periods can refer to a continuous or discrete time interval preceding the current moment. Optionally, historical time periods include the past day, past week, past month, or past three months. The duration of the historical time period should meet the requirement of "covering multiple scenarios and supporting sufficient model training" (e.g., including at least one scenario such as weekday morning rush hour, holiday off-peak, and late-night low-load). The selection of historical time periods should balance "sufficient data volume" and "scenario diversity," avoiding underfitting due to insufficient data volume or poor model adaptability due to outdated data (e.g., data from a year ago). Historical bandwidth usage data refers to a structured dataset collected within the historical time period, containing historical moments and their corresponding historical bandwidth performance values, serving as the foundational sample data for training machine learning models. The data format of historical bandwidth usage data can include binary tuples, including a historical moment and its corresponding historical bandwidth performance value. A historical moment is a specific point in time within the historical time period, with precision consistent with the current moment (e.g., second-level or minute-level). A historical moment can serve as the time anchor for historical bandwidth usage data, ensuring that each historical bandwidth performance value corresponds to a specific historical scenario. Historical bandwidth performance value refers to a quantified value of the actual bandwidth resource utilization effect within a target area at a specific historical moment. Optionally, the quantification indicators of historical bandwidth performance value may include at least one of the following: bandwidth utilization rate; transmission latency; packet loss rate; and a performance score obtained through weighted calculation.

[0075] In this embodiment, the historical time period of the data to be used can be determined, and multiple historical moments and their corresponding historical bandwidth efficiency values ​​of the target area within the historical time period can be obtained from the database associated with the target area based on the time identifier of the historical time period. Based on the multiple historical moments and their corresponding historical bandwidth efficiency values, multiple sets of historical bandwidth usage data can be determined.

[0076] S220. Train a pre-built machine learning model based on multiple sets of historical bandwidth usage data to obtain the target performance value after training and determine the model.

[0077] The pre-built machine learning model can be an algorithmic model that has already been constructed and has the ability to determine its corresponding optimal bandwidth performance value based on historical time points. The machine learning model can be constructed from any model structure. The model structure of the machine learning model includes at least one of the following: BP neural network, deep learning model, and gradient boosting tree model. Optionally, the machine learning model includes an input layer, a hidden layer, an activation layer, and an output layer.

[0078] In this embodiment, after obtaining multiple sets of historical bandwidth usage data, these sets of historical bandwidth usage data can be used as training samples to train a pre-built machine learning model based on the multiple training samples, so as to obtain the target performance value determination model after training.

[0079] Optionally, a pre-built machine learning model is trained based on multiple sets of historical bandwidth usage data to obtain a target performance value determination model after training. This includes: inputting multiple sets of historical bandwidth usage data into the machine learning model to obtain multiple model prediction values; determining an average error value based on the multiple model prediction values ​​and the actual bandwidth performance values ​​in the multiple sets of historical bandwidth usage data; adjusting the model parameters of the machine learning model based on the average error value and a pre-determined training error value; and stopping training when the average error value is less than the training error value to obtain a target performance value determination model after training.

[0080] Here, the model prediction value refers to the predicted bandwidth efficiency value output by a machine learning model after inputting multiple sets of historical bandwidth usage data, corresponding to each historical moment. In other words, the model prediction value can be the predicted bandwidth efficiency value determined by the machine learning model based on historical bandwidth usage data. The average error value can be the statistical average value, calculated by comparing multiple model prediction values ​​with their corresponding actual bandwidth efficiency values, reflecting the overall model fit deviation. The average error value can be used to quantify the overall fitting accuracy of the model. The smaller the average error value, the closer the model prediction is to the true value, and the better the fit; conversely, the larger the average error value, the worse the fit. The training error value can be an error threshold determined based on the network demand of the target region; this error threshold can serve as the stopping condition for model training.

[0081] In this embodiment, the machine learning model includes an input layer, a hidden layer, an activation layer, and an output layer. Furthermore, multiple sets of historical bandwidth usage data are provided to the machine learning model, and the input, hidden, activation, and output layers of the machine learning model sequentially process these multiple sets of historical bandwidth usage data to obtain multiple model prediction values.

[0082] Optionally, multiple sets of historical bandwidth usage data are input into the machine learning model to obtain multiple model predictions at output, including: receiving multiple sets of historical bandwidth usage data through the input layer and passing the multiple sets of historical bandwidth usage data to the hidden layer; determining a first bandwidth feature matrix based on the first weight matrix and the first bias vector corresponding to the hidden layer and the multiple sets of historical bandwidth usage data; processing the first bandwidth feature matrix through the activation layer to obtain a second bandwidth feature matrix; and determining multiple model predictions based on the second weight matrix and the second bias vector corresponding to the output layer and the second bandwidth feature matrix.

[0083] The input layer, the outermost layer of the BP neural network, is the data entry point for the model to receive multiple sets of historical bandwidth usage data. It consists of neurons whose dimensions match the input data. The input layer is used for data reception and direct transmission, without performing any feature transformation or computation. The hidden layer, located between the input and output layers, is the core computational layer, composed of a predetermined number of neurons. It is the core module for the model to extract deep features from the bandwidth data. The hidden layer can transform the raw data of the input layer into bandwidth features through linear transformations of the weight matrix, input data, and bias vector. The activation layer can be a non-linear transformation module closely bound to the hidden layer. It performs a non-linear mapping on the linear feature matrix output by the hidden layer through an activation function, enabling the model to learn the non-linear correlations in the historical bandwidth usage data. Optionally, the activation function includes the ReLU activation function. The output layer, the innermost layer of the BP neural network, is the output of multiple model predictions. It consists of neurons whose dimensions match the prediction target. The output layer performs a linear transformation on the non-linear feature matrix output by the activation layer, mapping abstract features into directly interpretable model predictions.

[0084] The first weight matrix can be the feature mapping coefficient matrix corresponding to the hidden layer, with dimensions of [number of neurons in the input layer × number of neurons in the hidden layer]. It is one of the core optimization parameters during model training. Each element in the first weight matrix represents the connection strength between the i-th neuron in the input layer and the j-th neuron in the hidden layer. The larger the weight value, the more significant the influence of the input feature on the hidden layer feature. The weight values ​​in the first weight matrix are random values ​​in the early stages of training and are iteratively adjusted through backpropagation to gradually approach the optimal value. The first bias vector can be the offset adjustment vector corresponding to the hidden layer, with dimensions of [1 × number of neurons in the hidden layer]. It is an auxiliary parameter optimized during model training. Each element in the first bias vector represents the output offset of the j-th neuron in the hidden layer, used to adjust the baseline of the linear transformation and avoid the model only fitting a linear relationship passing through the origin. The second weight matrix can be the feature mapping coefficient matrix corresponding to the output layer, with dimensions of [number of neurons in the hidden layer × number of neurons in the output layer]. It is one of the core optimization parameters during model training. Each element in the second weight matrix represents the connection strength between the j-th neuron in the hidden layer and the k-th neuron in the output layer. A larger weight value indicates a more significant impact of the hidden layer features on the predicted output value. The second bias vector can be an offset adjustment vector corresponding to the output layer, with a dimension of [1 × number of neurons in the output layer]. It is an auxiliary parameter optimized during model training. Each element in the second bias vector represents the output offset of the k-th neuron in the output layer, used to adjust the baseline of the final linear transformation and improve the model's fitting accuracy to the actual bandwidth performance value. The first bandwidth feature matrix can be the preliminary feature matrix output by the hidden layer after performing a linear transformation on the input data based on the first weight matrix and the first bias vector, with a dimension of [number of historical bandwidth usage data sets × number of hidden layer neurons]. The first bandwidth feature matrix can be used to transform the original historical bandwidth usage data into high-dimensional abstract features. Each element represents the feature response strength of a set of historical data on a certain hidden layer neuron, reflecting the deep linear correlation of the data. The second bandwidth feature matrix can be the nonlinear abstract feature matrix output by the activation layer after performing a nonlinear transformation on the first bandwidth feature matrix, with the same dimension as the first bandwidth feature matrix. The second bandwidth feature matrix can be used to filter out invalid negative features in the first bandwidth feature matrix, strengthen the nonlinear correlation of effective features, and make the features more suitable for the actual bandwidth pattern.

[0085] In one embodiment, multiple sets of historical bandwidth usage data can be provided to a machine learning model. The input layer of the machine learning model receives these historical bandwidth usage data and passes them to a hidden layer. Further, a first weight matrix corresponding to the hidden layer can be multiplied by the multiple sets of historical bandwidth usage data. The resulting matrix is ​​then added to a first bias vector, and this added matrix serves as the first bandwidth feature matrix, which is input to the activation layer. Further, the activation layer can perform a non-linear mapping on the first bandwidth feature matrix to obtain a second bandwidth feature matrix, which is then input to the output layer. Further, a second weight matrix corresponding to the output layer can be multiplied by the second bandwidth feature matrix. The resulting matrix is ​​then added to a second bias vector to obtain a matrix containing multiple model predictions. Thus, multiple model predictions obtained by the machine learning model can be obtained. Furthermore, the average error value can be determined based on multiple model predictions and historical bandwidth performance values ​​from multiple sets of historical bandwidth usage data. The average error value is then compared with a pre-determined training error value. If the average error value is not less than the training error value, the model parameters of the machine learning model can be adjusted. Multiple sets of historical bandwidth usage data are then provided to the machine learning model with adjusted parameters to continue the model training process until the average error value is less than the training error value. At this point, training stops, and the machine learning model at this stage is used as the target performance value for model training completion.

[0086] S230. Input multiple historical moments into the target performance value determination model to obtain the output historical target bandwidth performance value corresponding to each historical moment. Determine the historical bandwidth corresponding information based on the multiple historical moments and the historical target bandwidth performance values ​​corresponding to each historical moment.

[0087] In this embodiment, given the target performance value determination model, multiple historical time points can be input into the model. Then, the output historical target bandwidth performance value corresponding to each historical time point can be obtained. Furthermore, structured historical bandwidth correspondence information can be constructed based on the multiple historical time points and the historical target bandwidth performance values ​​corresponding to each historical time point.

[0088] S240. Obtain the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current time.

[0089] S250. Determine the first target bandwidth performance value corresponding to the current time from the pre-determined historical bandwidth information based on the current time.

[0090] S260. Process the bandwidth allocation data according to the preset bandwidth allocation algorithm to obtain the target bandwidth allocation data corresponding to the current time.

[0091] S270. Based on the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, determine the target performance threshold corresponding to the target area at the current time, and adjust the bandwidth allocation strategy of the target area according to the target performance threshold.

[0092] The technical solution of this invention involves acquiring multiple sets of historical bandwidth usage data for a target area within a historical time period. These historical bandwidth usage data include historical moments and corresponding historical bandwidth efficiency values. Further, a pre-built machine learning model is trained based on these multiple sets of historical bandwidth usage data to obtain a trained target efficiency value determination model. Further, multiple historical moments are input into the target efficiency value determination model to obtain output historical target bandwidth efficiency values ​​corresponding to each historical moment. Based on these multiple historical moments and their corresponding historical target bandwidth efficiency values, historical bandwidth correspondence information is determined. This process transforms fragmented historical bandwidth usage data into directly reusable historical bandwidth correspondence information. Furthermore, model training filters outliers and enhances pattern adaptability, providing accurate and reliable historical reference support for quickly matching the first target bandwidth efficiency value at the current moment. This avoids the blindness of current bandwidth allocation decisions lacking historical basis and lays a solid historical data foundation for the dynamic optimization of the overall bandwidth allocation strategy.

[0093] Example 3

[0094] Figure 3 This is a schematic diagram of a communication bandwidth adjustment device provided in Embodiment 3 of the present invention. Figure 3As shown, the device includes: a data acquisition module 310, a first bandwidth data determination module 320, a second bandwidth data determination module 330, and a performance threshold determination module 340. The system includes a data acquisition module 310, used to acquire the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current time; wherein the bandwidth allocation data is used to characterize the communication network operation status of the target area at the current time; a first bandwidth data determination module 320, used to determine the first target bandwidth efficiency value corresponding to the current time from pre-determined historical bandwidth correspondence information based on the current time; wherein the historical bandwidth correspondence information is determined based on a pre-trained target efficiency value determination model and historical bandwidth usage data within the target area; the historical bandwidth correspondence information is used to characterize the correspondence between historical times and historical target bandwidth efficiency values; a second bandwidth data determination module 330, used to process the bandwidth allocation data according to a preset bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current time; wherein the target bandwidth allocation data includes a second target bandwidth efficiency value and a target bandwidth allocation weight; and an efficiency threshold determination module 340, used to determine the target efficiency threshold corresponding to the target area at the current time based on the actual bandwidth efficiency value, the first target bandwidth efficiency value, and the target bandwidth allocation data, so as to adjust the bandwidth allocation strategy of the target area according to the target efficiency threshold.

[0095] The technical solution of this invention obtains the actual bandwidth efficiency value and bandwidth allocation data of the target area at the current moment. The bandwidth allocation data is used to characterize the communication network operation status of the target area at the current moment, capturing the real effect of the current bandwidth usage and the communication network operation status (including resource constraints, service requirements, etc.) in real time. This provides accurate input for the subsequent generation of target bandwidth allocation data by the slime mold algorithm, dynamic determination of the target efficiency threshold, and precise adjustment of the bandwidth allocation strategy, ensuring that bandwidth optimization fits the current network scenario. Furthermore, by determining the first target bandwidth efficiency value corresponding to the current moment from pre-determined historical bandwidth information, and leveraging the historical optimal bandwidth efficiency pattern of the target area, an accurate historical reference benchmark is provided for the current moment, directly supporting the dynamic calculation of the target efficiency threshold and improving the targeting and rationality of subsequent bandwidth allocation strategy adjustments. Furthermore, by processing the bandwidth allocation data according to a preset bandwidth allocation algorithm, target bandwidth allocation data corresponding to the current moment is obtained, providing an objective theoretical benchmark for subsequent target efficiency threshold calculation and precise adjustment of the bandwidth strategy, ensuring the efficiency and adaptability of bandwidth allocation. Furthermore, based on the actual bandwidth efficiency value, the first target bandwidth efficiency value, and the target bandwidth allocation data, a target efficiency threshold corresponding to the target area at the current moment is determined. The bandwidth allocation strategy for the target area is then adjusted according to this target efficiency threshold. By integrating the current actual bandwidth efficiency, historical best references, and theoretically optimal allocation schemes, a precise target efficiency threshold adapted to the current scenario is determined, providing a clear basis for bandwidth allocation strategy adjustments and achieving dynamic optimization and highly adaptable scheduling of bandwidth resources. The technical solution of this invention addresses the limitations of bandwidth resource allocation strategies in related technologies, which lead to poor bandwidth resource allocation effects. It achieves the effect of dynamically determining a target efficiency threshold adapted to the current scenario based on historical target bandwidth efficiency values, target bandwidth allocation data, and actual bandwidth efficiency values, and dynamically adjusting the bandwidth allocation strategy at the current moment based on the target efficiency threshold. This achieves precise and dynamic adjustment of the bandwidth allocation strategy, improves bandwidth resource utilization and network node load balancing, enhances the efficiency of dynamic bandwidth resource allocation, significantly optimizes the allocation effect of bandwidth resources in the target area, and adapts to the complex needs of dynamic communication scenarios such as vehicle-to-everything (V2X) communication.

[0096] Optionally, the device further includes: a historical data acquisition module, a model training module, a historical bandwidth performance value determination module, and a historical bandwidth correspondence information determination module. The historical data acquisition module is used to acquire multiple sets of historical bandwidth usage data for a target area within a historical time period; wherein the historical bandwidth usage data includes historical times and the historical bandwidth performance value corresponding to each historical time. The model training module is used to train a pre-built machine learning model based on the multiple sets of historical bandwidth usage data to obtain a trained target performance value determination model. The historical bandwidth correspondence information determination module is used to input multiple historical times into the target performance value determination model to obtain an output historical target bandwidth performance value corresponding to each historical time, and determine historical bandwidth correspondence information based on the multiple historical times and the historical target bandwidth performance values ​​corresponding to each historical time.

[0097] Optionally, the model training module includes: a model prediction value determination unit, a parameter adjustment unit, and a model determination unit. The model prediction value determination unit is used to input multiple sets of historical bandwidth usage data into the machine learning model to obtain multiple output model prediction values. The model training unit is used to determine an average error value based on the multiple model prediction values ​​and historical bandwidth performance values ​​from the multiple sets of historical bandwidth usage data, and to adjust the model parameters of the machine learning model based on the average error value and a pre-determined training error value. The model determination unit is used to stop training when the average error value is less than the training error value, thus obtaining a trained target performance value determination model.

[0098] Optionally, the machine learning model includes an input layer, a hidden layer, an activation layer, and an output layer; the model prediction value determination unit is specifically used to receive multiple sets of historical bandwidth usage data through the input layer and pass the multiple sets of historical bandwidth usage data to the hidden layer; determine a first bandwidth feature matrix based on a first weight matrix and a first bias vector corresponding to the hidden layer and the multiple sets of historical bandwidth usage data; process the first bandwidth feature matrix through the activation layer to obtain a second bandwidth feature matrix; and determine multiple model prediction values ​​based on a second weight matrix and a second bias vector corresponding to the output layer and the second bandwidth feature matrix.

[0099] Optionally, the first bandwidth data determination module 320 is specifically used to determine the historical time associated with the current time from the pre-determined historical bandwidth corresponding information, and to determine the historical target bandwidth efficiency value corresponding to the determined historical time as the first target bandwidth efficiency value corresponding to the current time.

[0100] Optionally, the second bandwidth data determination module 330 includes a target bandwidth data determination unit. The target bandwidth data determination unit is used to process the bandwidth allocation data according to the slime mold foraging algorithm to obtain target bandwidth allocation data corresponding to the current time.

[0101] Optionally, the performance threshold determination module 340 includes a distance determination unit and a performance threshold determination unit. The distance determination unit is used to determine a first distance between the actual bandwidth performance value and the first target bandwidth performance value; and to determine a second distance between the actual bandwidth performance value and the target bandwidth allocation data. The performance threshold determination unit is used to determine a target performance threshold corresponding to the target region at the current time based on the first distance, the second distance, the first target bandwidth performance value, and the second target bandwidth performance value.

[0102] The communication bandwidth adjustment device provided in this embodiment of the invention can execute the communication bandwidth adjustment method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0103] Example 4

[0104] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0105] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0106] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0107] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as communication bandwidth adjustment methods.

[0108] In some embodiments, the communication bandwidth adjustment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the communication bandwidth adjustment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the communication bandwidth adjustment method by any other suitable means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), target blockchain networks, and the Internet.

[0114] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0115] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0116] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0117] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of adjusting a communication bandwidth, characterized by, The method comprises the following steps: obtaining an actual bandwidth performance value corresponding to a target region at a current time and bandwidth allocation data; wherein the bandwidth allocation data is used to represent the running state of a communication network corresponding to the target region at the current time; determining a first target bandwidth performance value corresponding to the current time from pre-determined historical bandwidth corresponding information; wherein the historical bandwidth corresponding information is determined based on a pre-trained target performance value determination model and historical bandwidth usage data in the target region; the historical bandwidth corresponding information is used to represent the corresponding relationship between historical time and historical target bandwidth performance value; processing the bandwidth allocation data according to a pre-set bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current time; wherein the target bandwidth allocation data comprises a second target bandwidth performance value and a target bandwidth allocation weight; determining a target performance threshold value corresponding to the target region at the current time according to the actual bandwidth performance value, the first target bandwidth performance value and the target bandwidth allocation data, so as to adjust the bandwidth allocation strategy of the target region according to the target performance threshold value.

2. The communication bandwidth adjustment method according to claim 1, characterized by, The method further comprises the following steps: obtaining a plurality of sets of historical bandwidth usage data of a target region within a historical time period; wherein the historical bandwidth usage data comprises a historical time and a historical bandwidth performance value corresponding to the historical time; training a pre-constructed machine learning model according to a plurality of sets of historical bandwidth usage data to obtain a trained target performance value determination model; inputting a plurality of historical times into the target performance value determination model to obtain outputted historical target bandwidth performance values corresponding to each of the historical times respectively, and determining historical bandwidth corresponding information according to a plurality of historical times and historical target bandwidth performance values corresponding to the historical times respectively.

3. The communication bandwidth adjustment method according to claim 2, characterized by, The step of training a pre-constructed machine learning model according to a plurality of sets of historical bandwidth usage data to obtain a trained target performance value determination model comprises the following steps: inputting a plurality of sets of historical bandwidth usage data into the machine learning model to obtain outputted a plurality of model prediction values; determining an average error value according to a plurality of model prediction values and historical bandwidth performance values in a plurality of sets of historical bandwidth usage data, and adjusting model parameters of the machine learning model according to the average error value and a pre-determined training error value; stopping training to obtain a trained target performance value determination model in the case that the average error value is less than the training error value.

4. The communication bandwidth adjustment method according to claim 3, characterized by, The machine learning model comprises an input layer, a hidden layer, an activation layer and an output layer; the step of inputting a plurality of sets of historical bandwidth usage data into the machine learning model to obtain outputted a plurality of model prediction values comprises the following steps: receiving a plurality of sets of historical bandwidth usage data through the input layer, and passing the plurality of sets of historical bandwidth usage data to the hidden layer; determining a first bandwidth feature matrix according to a first weight matrix and a first bias vector corresponding to the hidden layer and a plurality of sets of historical bandwidth usage data; The first bandwidth feature matrix is processed by the activation layer to obtain a second bandwidth feature matrix; A plurality of model prediction values are determined according to a second weight matrix and a second bias vector corresponding to the output layer and the second bandwidth feature matrix.

5. The method of claim 1, wherein, The first target bandwidth performance value corresponding to the current moment is determined from the predetermined historical bandwidth corresponding information, including: The historical moment associated with the current moment is determined from the predetermined historical bandwidth corresponding information, and the historical target bandwidth performance value corresponding to the determined historical moment is determined as the first target bandwidth performance value corresponding to the current moment.

6. The method of claim 1, wherein, The target bandwidth allocation data corresponding to the current moment is obtained by processing the bandwidth allocation data according to a preset bandwidth allocation algorithm, including: The target bandwidth allocation data corresponding to the current moment is obtained by processing the bandwidth allocation data according to a myzak foraging algorithm.

7. The method of claim 1, wherein, The target performance threshold value of the target area corresponding to the current moment is determined according to the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, including: A first distance between the actual bandwidth performance value and the first target bandwidth performance value is determined, and a second distance between the actual bandwidth performance value and the target bandwidth allocation data is determined. The target performance threshold value of the target area corresponding to the current moment is determined according to the first distance, the second distance, the first target bandwidth performance value, and the second target bandwidth performance value.

8. A communication bandwidth adjustment apparatus, characterized by comprising: It includes: The data acquisition module is used for acquiring the actual bandwidth performance value and the bandwidth allocation data corresponding to the current moment of the target area; wherein the bandwidth allocation data is used to represent the communication network running state of the target area corresponding to the current moment; The first bandwidth data determination module is used for determining the first target bandwidth performance value corresponding to the current moment from the predetermined historical bandwidth corresponding information according to the current moment; wherein the historical bandwidth corresponding information is determined based on the target performance value determination model trained in advance and the historical bandwidth usage data in the target area; the historical bandwidth corresponding information is used to represent the corresponding relationship between the historical moment and the historical target bandwidth performance value; The second bandwidth data determination module is used for processing the bandwidth allocation data according to a preset bandwidth allocation algorithm to obtain target bandwidth allocation data corresponding to the current moment; wherein the target bandwidth allocation data includes a second target bandwidth performance value and a target bandwidth allocation weight. The performance threshold value determination module is used for determining the target performance threshold value of the target area corresponding to the current moment according to the actual bandwidth performance value, the first target bandwidth performance value, and the target bandwidth allocation data, so as to adjust the bandwidth allocation strategy of the target area according to the target performance threshold value.

9. An electronic device, comprising: The electronic device includes: At least one processor; and The memory is connected in communication with the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the communication bandwidth adjustment method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to implement the communication bandwidth adjustment method in any one of claims 1-7 when executed.

Images