Resource reservation method and device and wireless network equipment

Abstract

The invention relates to the technical field of communication, in particular to a resource reservation method and device and wireless network equipment. The method comprises the following steps: acquiring wireless environment characteristics of an environment where wireless network equipment is located in a target time period, a network load condition of a wireless communication network provided by the wireless network equipment in the target time period, and a resource scheduling strategy adopted by the wireless network equipment for the wireless environment characteristics and the network load condition in the target time period; determining communication resources reserved for the wireless communication network in the future time period according to the wireless environment characteristics, the network load condition and a resource scheduling strategy; wherein the future time period is later than the target time period.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a resource reservation method, device and wireless network equipment. Background Art

[0002] In modern communication systems, wireless networks serve as a bridge between mobile devices and core networks, and undertake key data transmission tasks. Wireless resource allocation is crucial in wireless networks, which directly affects network capacity, coverage, and user communication experience.

[0003] To address these challenges, resource reservation has become a key strategy to solve the bottleneck of wireless resource allocation. By reserving certain bandwidth or spectrum resources for key services or burst traffic, the network can maintain stable operation under high load and burst conditions, ensuring service quality.

[0004] However, existing resource reservation methods usually rely on static or semi-dynamic configuration, which cannot fully cope with the rapid changes in network demand, resulting in low resource utilization efficiency and inability to flexibly adjust according to actual conditions. Summary of the invention

[0005] Based on this, it is necessary to provide a resource reservation method, device and wireless network equipment that can optimize the resource reservation effect in response to the above technical problems.

[0006] In a first aspect, the present application provides a resource reservation method, the method comprising:

[0007] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0008] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future period are determined; wherein the future period is later than the target period.

[0009] In one embodiment, obtaining a resource scheduling strategy adopted by a wireless network device in a target period according to wireless environment characteristics and network load conditions includes:

[0010] Determine the communication configuration strategy adopted by the wireless network device in the target period according to the modulation and coding strategy MCS, transmission rank RANK and transmission power of the wireless network device;

[0011] Determine the resource allocation strategy adopted by the wireless network device in the target period according to the amount of available resources provided by the wireless network device to the terminal device connected to the wireless communication network in the target period and the data throughput between the wireless communication network and the terminal device in the target period;

[0012] According to the communication configuration strategy and resource allocation strategy, the resource scheduling characteristics adopted by the wireless network equipment in the target time period according to the wireless environment characteristics and network load conditions are determined.

[0013] In one embodiment, obtaining the wireless environment characteristics of the environment in which the wireless network device is located during the target period includes:

[0014] The wireless environment characteristics of the environment where the wireless network device is located in the target period are determined according to the signal strength RSRP of the wireless communication network in the target period and the signal to interference plus noise ratio SINR fed back by the terminal device connected to the wireless communication network in the target period.

[0015] In one embodiment, obtaining the network load of the wireless communication network provided by the wireless network device during the target time period includes:

[0016] The network load of the wireless communication network in the target time period is determined according to the number of connection requests RRC received by the wireless communication network in the target time period, the maximum number of connected users corresponding to the wireless communication network, and the average number of connected users of the wireless communication network.

[0017] In one embodiment, determining communication resources reserved for a wireless communication network in a future period according to wireless environment characteristics, network load conditions, and resource scheduling strategies includes:

[0018] Inputting the wireless environment characteristics into the first analysis model to obtain the environmental impact characteristics;

[0019] Inputting the network load condition into the second analysis model to obtain the load impact characteristics;

[0020] Input the resource scheduling strategy into the third analysis model to obtain scheduling impact characteristics;

[0021] Perform feature fusion on environmental impact features, load impact features and scheduling impact features to obtain network fusion features;

[0022] The network fusion features are input into the prediction model to obtain the communication resources reserved for the wireless communication network in the future period.

[0023] In one embodiment, the environmental impact feature, the load impact feature, and the scheduling impact feature are integrated to obtain a network integration feature, including:

[0024] Input the environmental impact feature, the load impact feature, and the scheduling impact feature into the self-attention module to obtain a first feature weight corresponding to the environmental impact feature, a second feature weight corresponding to the load impact feature, and a third feature weight corresponding to the scheduling impact feature;

[0025] The network fusion feature is determined according to the product of the environmental impact feature and the first feature weight, the product of the load impact feature and the second feature weight, and the product of the scheduling impact feature and the third feature weight.

[0026] In a second aspect, the present application further provides a resource reservation device, including:

[0027] An acquisition module is used to acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0028] The resource reservation module is used to determine the communication resources reserved for the wireless communication network in a future period according to the wireless environment characteristics, network load conditions and resource scheduling strategy; wherein the future period is later than the target period.

[0029] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0030] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0031] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future time period are determined; wherein the future time period is later than the target time period.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0034] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future period are determined; wherein the future period is later than the target period.

[0035] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0036] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0037] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future period are determined; wherein the future period is later than the target period.

[0038] The above-mentioned resource reservation method, device and wireless network equipment, this application comprehensively considers information from multiple dimensions such as wireless environment characteristics, network load conditions and resource scheduling strategies, and adopts an automatic and intelligent analysis method to capture the changing trend of wireless network resource demand in the time series of the target period. This technical solution can accurately predict future resource demand. By dynamically adjusting the resource reservation ratio, this technical solution can make more effective use of wireless resources. This helps to avoid excessive waste and shortage of resources, thereby improving resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 An application environment diagram of a resource reservation method in an embodiment;

[0041] Figure 2 A schematic diagram of a flow chart of a resource reservation method in an embodiment;

[0042] Figure 3 A schematic diagram of a flow chart of steps for obtaining a resource scheduling strategy adopted by a wireless network device in a target time period according to wireless environment characteristics and network load conditions in an embodiment;

[0043] Figure 4A schematic diagram of a flow chart of a step of determining communication resources reserved for a wireless communication network in a future period in one embodiment;

[0044] Figure 5 A schematic diagram of a flow chart of steps for obtaining network fusion characteristics in one embodiment;

[0045] Figure 6 A schematic diagram of a network model corresponding to a resource reservation method in another embodiment;

[0046] Figure 7 is a structural block diagram of a resource reservation device in an embodiment;

[0047] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] The resource reservation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the wireless network device 104 through the network.

[0050] In an exemplary embodiment, Figure 2 As shown, a resource reservation method is provided, which is applied to Figure 1 The application in the wireless network device 104 is used as an example for explanation, wherein:

[0051] S201, obtaining wireless environment characteristics of the environment in which the wireless network device is located during the target period, network load conditions of the wireless communication network provided by the wireless network device during the target period, and resource scheduling strategies adopted by the wireless network device during the target period according to the wireless environment characteristics and network load conditions.

[0052] Among them, wireless environment characteristics refer to the comprehensive performance of factors such as radio wave propagation conditions, interference conditions, signal coverage, etc. in the environment where wireless network equipment is located. These characteristics directly affect the performance and quality of wireless communication networks.

[0053] For example, in an indoor wireless environment, wireless environment characteristics may include the shielding effect of the building, the influence of indoor furnishings, the separation loss of floors, etc. In a vehicle-mounted wireless environment, wireless environment characteristics may include the moving speed of the vehicle, the average power of the received signal decreases exponentially with the increase of distance, etc.

[0054] Optionally, the method of obtaining wireless environment characteristics can include direct acquisition and indirect acquisition through signal quality. The following are specific descriptions of these two methods: 1) Use specialized radio measurement equipment, such as spectrum analyzers, signal strength testers, etc. to directly measure the wireless environment. These devices can accurately obtain various parameters of the wireless environment, such as signal strength, noise level, channel occupancy, etc. 2) Indirectly infer the characteristics of the wireless environment by monitoring the signal quality indicators of wireless communication equipment, such as bit error rate, packet loss rate, delay, etc. For example, a higher bit error rate may mean that there is strong interference or signal attenuation in the wireless environment.

[0055] The network load refers to the data transmission pressure and working intensity of the wireless network equipment in a specific period of time. It directly reflects the working status of the network. The size of the network load directly affects the response speed, data transmission efficiency and stability of the network.

[0056] For example, when the network load is light, the devices in the network can easily process the transmitted data, the response time is fast, and the data transmission efficiency is high. As the network load increases, the amount of data that the devices in the network need to process increases, which may lead to longer response times, lower data transmission efficiency, and even network congestion and failure.

[0057] Among them, resource scheduling strategy refers to the wireless network equipment dynamically adjusting and optimizing the allocation and use of resources in the wireless communication network according to the characteristics of the wireless environment and the network load to improve network performance and quality. These resources may include spectrum, power, antennas, and bandwidth. The goal of the resource scheduling strategy is to ensure that the user's communication needs are met with the least resources under limited communication resources, while improving the network's capacity, throughput, and user experience.

[0058] For example, in dynamic resource optimization, wireless network equipment can use strategies such as dynamic power control, dynamic spectrum allocation and sharing based on real-time information such as network load and environmental changes to adjust the allocation and use of network resources in real time to adapt to different user needs and network conditions.

[0059] Optionally, the resource scheduling strategy is obtained by taking the uplink modulation and coding scheme (MCS), physical resource block (PRBk), transmission rank (RANK) and transmission power as model inputs, and using a neural network to extract information such as the wireless resource scheduling strategy adopted for the current wireless environment. This information can reflect the resource usage and the effect of the scheduling strategy in the current network environment, thereby providing a decision basis for subsequent resource reservation and scheduling.

[0060] S202: Determine the communication resources reserved for the wireless communication network in a future period according to the wireless environment characteristics, network load conditions and resource scheduling strategy.

[0061] Among them, the future period is later than the target period.

[0062] It is understandable that wireless environment characteristics usually include wireless environment characteristics such as RSRP (reference signal received power) and SINR (signal to interference plus noise ratio). These data reflect the pros and cons of the current wireless environment and are the basis for the prediction model to judge future resource requirements.

[0063] The network load situation includes network load situation and resource scheduling strategy, such as uplink PDCP throughput, number of RRC connection requests, maximum number of RRC users, average number of RRC users, etc. These data provide detailed information about the current network usage and help the model predict future network load.

[0064] Resource Scheduling Strategy Through the input of uplink MCS, PRB, RANK and transmit power parameters, the neural network can extract the resource scheduling strategy adopted in the current network environment. These strategies reflect how the network allocates and manages resources and are an important reference for predicting future resource requirements.

[0065] Optionally, wireless environment characteristics, network load conditions and resource scheduling strategies are input into a prediction model to obtain communication resources reserved for the wireless communication network in a future period output by the prediction model.

[0066] Specifically, the above wireless environment characteristics, network load conditions and resource scheduling strategies are used as inputs and sent to the trained prediction model, which is an RNN model. The RNN model is suitable for processing sequence data and can capture dependencies in time series, which is crucial for predicting future resource requirements. The RNN model passes the information of the previous time step to the next time step through its internal hidden state, thereby capturing the time dependency in the sequence data. This enables the model to predict future network status and resource requirements based on historical data. After being processed by the RNN model, the communication resources reserved for the wireless communication network in the future period are output.

[0067] The above resource reservation method, this application comprehensively considers information from multiple dimensions such as wireless environment characteristics, network load conditions, and resource scheduling strategies, and adopts an automatic and intelligent analysis method to capture the changing trend of wireless network resource requirements in the time series of the target period. This technical solution can accurately predict future resource requirements. By dynamically adjusting the resource reservation ratio, this technical solution can make more effective use of wireless resources. This helps to avoid excessive waste and shortage of resources, thereby improving resource utilization efficiency.

[0068] In an exemplary embodiment, Figure 3 As shown, the resource scheduling strategy adopted by the wireless network device in the target period according to the wireless environment characteristics and network load conditions is obtained, including:

[0069] S301, determining a communication configuration strategy adopted by the wireless network device in a target period according to the modulation and coding strategy MCS, transmission rank RANK and transmission power of the wireless network device according to the wireless environment characteristics.

[0070] Modulation and Coding Strategy (MCS): MCS determines the modulation mode and coding rate of data transmission, which directly affects the reliability and rate of data transmission. Different MCS levels correspond to different modulation and coding methods to adapt to different wireless environment characteristics (such as signal strength, interference level, etc.).

[0071] Transmission rank (RANK): RANK represents the number of parallel data streams transmitted in multi-antenna transmission technology. It reflects the ability of wireless network equipment to improve data transmission rate by using multi-antenna technology. The selection of transmission rank depends on the spatial characteristics of the wireless environment, such as the rank of the channel matrix.

[0072] Transmit power: Transmit power determines the strength of the signal sent by the wireless network device. In wireless communications, transmit power is one of the key factors affecting signal coverage and reception quality. By adjusting the transmit power, wireless network devices can adapt to different wireless environment characteristics and ensure reliable signal transmission.

[0073] Taking the above factors into consideration, wireless network equipment can select the appropriate MCS level, transmission rank and transmit power according to the current wireless environment characteristics (such as signal quality, interference level, etc.), thereby determining the communication configuration strategy within the target time period.

[0074] S302, determining a resource allocation strategy to be adopted by the wireless network device in response to wireless environment characteristics and network load conditions during the target period of time, based on the amount of available resources provided by the wireless network device to the terminal device connected to the wireless communication network during the target period of time, and the data throughput between the wireless communication network and the terminal device.

[0075] Available resources: This usually refers to the number of physical resource blocks (PRBs) or other forms of resources (such as time, frequency, etc.) that the wireless network equipment can allocate to the terminal device for use within the target period.

[0076] Data throughput: Data throughput reflects the rate and efficiency of data transmission between the wireless communication network and the terminal device. It depends on many factors, including wireless environment characteristics, network load conditions, terminal device performance, etc.

[0077] Wireless network equipment needs to reasonably allocate available resources based on the current wireless environment characteristics and network load conditions, as well as the actual needs of terminal devices (such as data throughput requirements). This includes determining how much resources should be allocated to each terminal device, when to allocate resources, and how to allocate resources.

[0078] S303: Determine resource scheduling characteristics adopted by the wireless network device in the target time period according to the communication configuration strategy and the resource allocation strategy according to the wireless environment characteristics and the network load conditions.

[0079] In this embodiment, by integrating the communication configuration strategy and the resource allocation strategy, the wireless network device can form a complete resource scheduling solution, which not only takes into account the current wireless environment characteristics and network load conditions, but also takes into account the actual needs and performance limitations of the terminal devices.

[0080] In an exemplary embodiment, the wireless environment characteristics of the environment in which the wireless network device is located in the target time period are obtained, including: determining the wireless environment characteristics of the environment in which the wireless network device is located in the target time period based on the signal strength RSRP of the wireless communication network in the target time period, and the signal to interference plus noise ratio SINR fed back by the terminal device connected to the wireless communication network in the target time period.

[0081] Signal strength RSRP (Reference Signal Received Power): RSRP refers to the power of the reference signal received by the terminal device from the wireless network device. RSRP is an important indicator for measuring the strength of wireless signal coverage. A higher RSRP value indicates stronger signal coverage and better communication quality between the terminal device and the wireless network device. The wireless communication network will measure and report the RSRP value regularly or in real time so that the wireless network device can understand the current signal coverage.

[0082] Signal to Interference plus Noise Ratio (SINR): SINR refers to the ratio of the useful signal power received by the terminal device to the sum of the interference signal power and the noise power received. SINR is a key indicator for measuring the quality of wireless communication links. A higher SINR value indicates that the useful signal has a greater advantage over interference and noise, and the communication quality is better. The terminal device will periodically or in real time feedback the SINR value it receives to the wireless network device so that the wireless network device can understand the current communication link quality.

[0083] After obtaining RSRP and SINR, the wireless network device can comprehensively judge the wireless environment characteristics of the target period based on the values ​​of these two parameters. For example, if the RSRP value is high and the SINR value is also high, it means that the wireless network device is in an environment with strong signal coverage and good communication link quality. At this time, the resource reservation ratio can be appropriately reduced to make full use of network resources.

[0084] If the RSRP value is low or the SINR value is low, it means that the signal coverage of the wireless network device is weak or the communication link quality is poor. At this time, the resource reservation ratio needs to be increased to ensure stable service in case of burst traffic or key business needs.

[0085] In this embodiment, by acquiring the signal strength RSRP of the wireless communication network in the target time period and the signal to interference plus noise ratio SINR fed back by the terminal device, the wireless network device can accurately understand the wireless environment characteristics of the environment in which it is located.

[0086] In an exemplary embodiment, the network load status of the wireless communication network provided by the wireless network device in the target time period is obtained, including: determining the network load status of the wireless communication network in the target time period according to the number of connection requests RRC received by the wireless communication network in the target time period, the maximum number of connected users corresponding to the wireless communication network, and the average number of connected users of the wireless communication network.

[0087] Connection request count RRC (Radio Resource Control): RRC connection request count refers to the number of connection requests received by the wireless communication network from the terminal device during the target period. RRC connection request count is one of the important indicators to measure the network load. A higher RRC connection request count indicates that the network is in a relatively busy state and requires more resources to handle connection requests. The wireless communication network will record and count the RRC connection request count in real time or periodically so that the wireless network equipment can understand the current network load.

[0088] Maximum number of connected users: The maximum number of connected users refers to the maximum number of online users that a wireless communication network can support at the same time. The maximum number of connected users is an important indicator for measuring network capacity and load capacity. Knowing the maximum number of connected users helps wireless network devices avoid exceeding network capacity when allocating resources, which can lead to a decrease in service quality. The maximum number of connected users is usually determined based on the planning and configuration of the wireless communication network, and is tested and verified during network construction or upgrades.

[0089] Average number of connected users: The average number of connected users refers to the average number of simultaneous online users actually supported by the wireless communication network during the target period. The average number of connected users is an important indicator for measuring the actual network load. By comparing the average number of connected users with the maximum number of connected users, you can understand the utilization and load of the network. The wireless communication network will count the average number of connected users in real time or periodically so that wireless network devices can understand the current network load.

[0090] After obtaining the number of RRC connection requests, the maximum number of connected users, and the average number of connected users, the wireless network device can comprehensively judge the network load during the target period based on the values ​​of these three parameters. For example, if the number of RRC connection requests is high, and the average number of connected users is close to or reaches the maximum number of connected users, it means that the network is in a high-load state, and the resource reservation ratio needs to be increased to cope with possible network congestion. If the number of RRC connection requests is low, and the average number of connected users is far lower than the maximum number of connected users, it means that the network is in a low-load state, and the resource reservation ratio can be appropriately reduced to make full use of network resources.

[0091] In an exemplary embodiment, Figure 4 As shown, according to the wireless environment characteristics, network load conditions and resource scheduling strategy, the communication resources reserved for the wireless communication network in the future period are determined, including:

[0092] S401: Input the wireless environment characteristics into a first analysis model to obtain the environment impact characteristics.

[0093] Optionally, the wireless environment features mainly reflect the physical characteristics of the environment in which the wireless communication network is located, such as signal strength, signal quality, etc. These features are crucial for predicting future network performance and resource requirements. The first analysis model is selected as a CNN model that can automatically learn and extract useful features from input data. By inputting wireless environment features into the CNN model, environmental impact features that reflect the impact of the environment on network performance can be obtained.

[0094] S402: Input the network load condition into the second analysis model to obtain load impact characteristics.

[0095] Optionally, the network load condition mainly reflects the current load status of the wireless communication network, such as the number of connection requests, the number of connected users, etc. This information is very important for understanding the busyness and resource utilization of the network. Similarly, the second analysis model is also selected as the CNN model. By inputting the network load condition into the CNN model, a load impact feature reflecting the impact of the network load on the network performance can be obtained.

[0096] S403: Input the resource scheduling strategy into the third analysis model to obtain scheduling impact characteristics.

[0097] Optionally, the resource scheduling strategy mainly reflects the current resource allocation and scheduling of the wireless communication network. Different resource scheduling strategies will have different effects on network performance and resource requirements. The third analysis model is also selected as a CNN model. By inputting the resource scheduling strategy into the CNN model, a scheduling impact feature reflecting the impact of the scheduling strategy on network performance can be obtained.

[0098] S404, performing feature fusion on the environmental impact feature, the load impact feature and the scheduling impact feature to obtain a network fusion feature.

[0099] After obtaining the environmental impact characteristics, load impact characteristics, and scheduling impact characteristics, these characteristics need to be fused. The purpose of feature fusion is to integrate feature information from different sources to form a more comprehensive and accurate network fusion feature. The network fusion feature integrates information from multiple aspects such as wireless environment, network load, and resource scheduling, and can more accurately reflect the resource demand of the wireless communication network in the future period.

[0100] Optional, such as Figure 5 As shown, the environmental impact features, load impact features and scheduling impact features are fused to obtain network fusion features, including:

[0101] S501, input the environmental impact feature, load impact feature and scheduling impact feature into the self-attention module to obtain the first feature weight corresponding to the environmental impact feature, the second feature weight corresponding to the load impact feature, and the third feature weight corresponding to the scheduling impact feature.

[0102] The self-attention mechanism is a feature fusion method that calculates the correlation between input features and assigns a weight to each feature accordingly. This weight reflects the importance of the feature in the fusion process. By inputting the environmental impact feature, load impact feature, and scheduling impact feature into the self-attention module, the weight corresponding to each feature can be obtained, namely the first feature weight (corresponding to the environmental impact feature), the second feature weight (corresponding to the load impact feature), and the third feature weight (corresponding to the scheduling impact feature).

[0103] S502, determining a network fusion feature according to a product of an environmental impact feature and a first feature weight, a product of a load impact feature and a second feature weight, and a product of a scheduling impact feature and a third feature weight.

[0104] After obtaining the weight corresponding to each feature, each feature is multiplied by its corresponding weight, and the results are added to obtain the network fusion feature. This process realizes the effective integration of different feature information. The network fusion feature integrates information from multiple aspects such as environmental impact features, load impact features, and scheduling impact features, and can more accurately reflect the resource demand of the wireless communication network in the future period.

[0105] S503: Input the network fusion features into the prediction model to obtain the communication resources reserved for the wireless communication network in the future period.

[0106] Optionally, the prediction model is a deep learning-based model that can learn the changing trend of future resource requirements from the input features. In this step, the network fusion features are used as the input of the prediction model. Through the calculation of the prediction model, the amount of communication resources reserved for the wireless communication network in the future period can be obtained. This resource reservation strategy can more effectively utilize wireless resources and improve the stability of the network and the communication experience of users.

[0107] In an exemplary embodiment, Figure 6 As shown in the figure, a network model corresponding to the above resource reservation method is provided. The network model adopts a multi-head mechanism, and takes three categories of information (wireless environment characteristics, network load conditions, and resource scheduling strategies) as the input of three sub-CNN neural networks respectively, processes these three categories of information separately, and independently learns the specific features of each category of data. In the feature fusion stage, the self-attention mechanism is introduced, and the outputs of the three neural networks are calculated by calculating the weight of each type of feature for resource reservation, and the proportion of each type of feature in the fusion process is dynamically adjusted. This model can combine the multi-dimensional information of wireless environment, resource scheduling, and network load to generate a more accurate resource reservation strategy.

[0108] Then, the RNN module (recursive neural network) processes the time series data, mainly used to capture the historical information of each network parameter index and rate and RB resource occupancy, so as to obtain the prediction results of future resources, generate effective resource reservation strategies to ensure the target rate. By inputting the effective features extracted by CNN, the output of the RNN module is the prediction result of future resource demand.

[0109] Finally, based on the prediction results of future resource demand, an effective resource reservation strategy is generated, and the resource reservation ratio is dynamically adjusted according to changes in future resource demand, thereby ensuring the user's speed and improving the user experience.

[0110] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a resource reservation device for implementing the resource reservation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more resource reservation device embodiments provided below can refer to the limitations on the resource reservation method above, and will not be repeated here.

[0112] In an exemplary embodiment, Figure 7 As shown, a resource reservation device is provided, comprising: an acquisition module 11 and a resource reservation module 12, wherein:

[0113] The acquisition module 11 is used to obtain the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period according to the wireless environment characteristics and the network load;

[0114] The resource reservation module 12 is used to determine the communication resources reserved for the wireless communication network in a future period according to the wireless environment characteristics, network load conditions and resource scheduling strategy; wherein the future period is later than the target period.

[0115] In one embodiment, the acquisition module 11 is further used to: acquire the resource scheduling strategy adopted by the wireless network device in the target time period according to the wireless environment characteristics and the network load conditions, including:

[0116] Determine the communication configuration strategy adopted by the wireless network device in the target period according to the modulation and coding strategy MCS, transmission rank RANK and transmission power of the wireless network device;

[0117] Determine the resource allocation strategy adopted by the wireless network device in the target period according to the amount of available resources provided by the wireless network device to the terminal device connected to the wireless communication network in the target period and the data throughput between the wireless communication network and the terminal device in the target period;

[0118] According to the communication configuration strategy and resource allocation strategy, the resource scheduling characteristics adopted by the wireless network equipment in the target time period according to the wireless environment characteristics and network load conditions are determined.

[0119] In one of the embodiments, the acquisition module 11 is also used to determine the wireless environment characteristics of the environment in which the wireless network device is located during the target time period based on the signal strength RSRP of the wireless communication network during the target time period and the signal to interference plus noise ratio SINR fed back by the terminal device connected to the wireless communication network during the target time period.

[0120] In one of the embodiments, the acquisition module 11 is also used to determine the network load of the wireless communication network in the target time period based on the number of connection requests RRC received by the wireless communication network in the target time period, the maximum number of connected users corresponding to the wireless communication network, and the average number of connected users of the wireless communication network.

[0121] In one embodiment, the resource reservation module 12 is further used to: input the wireless environment characteristics into the first analysis model to obtain the environment impact characteristics;

[0122] Inputting the network load condition into the second analysis model to obtain the load impact characteristics;

[0123] Input the resource scheduling strategy into the third analysis model to obtain scheduling impact characteristics;

[0124] Perform feature fusion on environmental impact features, load impact features and scheduling impact features to obtain network fusion features;

[0125] The network fusion features are input into the prediction model to obtain the communication resources reserved for the wireless communication network in the future period.

[0126] In one embodiment, the resource reservation module 12 is further used to: input the environment impact feature, the load impact feature and the scheduling impact feature into the self-attention module to obtain a first feature weight corresponding to the environment impact feature, a second feature weight corresponding to the load impact feature, and a third feature weight corresponding to the scheduling impact feature;

[0127] The network fusion feature is determined according to the product of the environmental impact feature and the first feature weight, the product of the load impact feature and the second feature weight, and the product of the scheduling impact feature and the third feature weight.

[0128] Each module in the resource reservation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0129] In an exemplary embodiment, a computer device is provided. The computer device may be a wireless network device, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store XX data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a resource reservation method is implemented.

[0130] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0131] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0132] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0133] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future time period are determined; wherein the future time period is later than the target time period.

[0134] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0135] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0136] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future time period are determined; wherein the future time period is later than the target time period.

[0137] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0138] Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load;

[0139] According to the wireless environment characteristics, network load conditions and resource scheduling strategy, communication resources reserved for the wireless communication network in a future time period are determined; wherein the future time period is later than the target time period.

[0140] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0142] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A resource reservation method, characterized in that: Applied to wireless network equipment, the method comprises: Acquire the wireless environment characteristics of the environment in which the wireless network device is located during the target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load; Determine the communication resources reserved for the wireless communication network in a future time period according to the wireless environment characteristics, the network load condition and the resource scheduling strategy; wherein the future time period is later than the target time period.

2. The method according to claim 1, characterized in that Acquiring a resource scheduling strategy adopted by the wireless network device in the target time period according to the wireless environment characteristics and the network load condition, including: Determine, according to the modulation and coding strategy MCS, transmission rank RANK and transmit power of the wireless network device, a communication configuration strategy adopted by the wireless network device for the wireless environment characteristics within the target time period; Determine, according to the amount of available resources provided by the wireless network device for the terminal device connected to the wireless communication network during the target period, and the data throughput between the wireless communication network and the terminal device, the resource allocation strategy adopted by the wireless network device during the target period for the wireless environment characteristics and the network load condition; According to the communication configuration strategy and the resource allocation strategy, the resource scheduling characteristics adopted by the wireless network device in the target time period according to the wireless environment characteristics and the network load conditions are determined.

3. The method according to claim 1, characterized in that: Acquiring wireless environment characteristics of the environment in which the wireless network device is located during a target period of time includes: The wireless environment characteristics of the environment in which the wireless network device is located in the target time period are determined based on the signal strength RSRP of the wireless communication network in the target time period and the signal to interference plus noise ratio SINR fed back by the terminal device connected to the wireless communication network in the target time period.

4. The method according to claim 1, characterized in that: Obtaining a network load condition of a wireless communication network provided by the wireless network device during the target time period includes: The network load of the wireless communication network in the target time period is determined according to the number of connection requests RRC received by the wireless communication network in the target time period, the maximum number of connected users corresponding to the wireless communication network, and the average number of connected users of the wireless communication network.

5. The method according to claim 1, characterized in that The determining, according to the wireless environment characteristics, the network load condition and the resource scheduling strategy, the communication resources reserved for the wireless communication network in a future period includes: Inputting the wireless environment characteristics into a first analysis model to obtain environmental impact characteristics; Inputting the network load condition into a second analysis model to obtain load impact characteristics; Inputting the resource scheduling strategy into a third analysis model to obtain scheduling impact characteristics; Performing feature fusion on the environmental impact feature, the load impact feature and the scheduling impact feature to obtain a network fusion feature; The network fusion features are input into a prediction model to obtain communication resources reserved for the wireless communication network in a future period.

6. The method according to claim 5, characterized in that The step of fusing the environmental impact feature, the load impact feature, and the scheduling impact feature to obtain a network fusion feature includes: Inputting the environmental impact feature, the load impact feature, and the scheduling impact feature into a self-attention module to obtain a first feature weight corresponding to the environmental impact feature, a second feature weight corresponding to the load impact feature, and a third feature weight corresponding to the scheduling impact feature; The network fusion feature is determined according to the product of the environmental impact feature and the first feature weight, the product of the load impact feature and the second feature weight, and the product of the scheduling impact feature and the third feature weight.

7. A resource reservation device, characterized in that: Configured in a wireless network device, the device comprises: An acquisition module, used to acquire the wireless environment characteristics of the environment in which the wireless network device is located during a target period, the network load of the wireless communication network provided by the wireless network device during the target period, and the resource scheduling strategy adopted by the wireless network device during the target period in response to the wireless environment characteristics and the network load; A resource reservation module is used to determine the communication resources reserved for the wireless communication network in a future time period according to the wireless environment characteristics, the network load situation and the resource scheduling strategy; wherein the future time period is later than the target time period.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images