Signal scheduling method based on 5G base station

Abstract

The invention discloses a signal scheduling method based on a 5G base station, and relates to the technical field of 5G communication, and the method comprises the following steps: carrying out the data collection in advance: collecting user equipment data, network state data and environment parameters in real time through a built-in sensor and a network monitoring unit of the base station; the collected data is preprocessed, specifically, the collected data is subjected to cleaning, duplicate removal and normalization processing, and non-standardized parameters are converted into a [0, 1] interval through a mapping formula; according to the method, the intelligent scheduling model driven by the multi-dimensional data is constructed, dynamic optimal configuration of 5G base station signal resources is achieved, environmental parameters such as path loss factors and shadow fading standard deviation and user service characteristics are fused, cooperative improvement of the coverage quality, the resource utilization rate, interference suppression and user experience is achieved through a multi-objective optimization function, and the user experience is improved. And the adaptability limitation of a traditional static scheduling mode in a complex scene is broken through.

Description

Technical Field

[0001] This invention relates to the field of 5G communication technology, and more specifically, to a signal scheduling method based on 5G base stations. Background Technology

[0002] With the rapid development and widespread application of 5G technology, 5G base stations, as a key infrastructure of 5G networks, need to support a wider variety of devices and service scenarios. Currently, 5G base stations face an increasing number of connected devices and diverse service demands. Traditional base station configurations and algorithms often struggle to meet the needs of these complex scenarios, leading to degraded network quality and poor user experience.

[0003] Traditional algorithms have several shortcomings in signal scheduling. For example, in coverage optimization, they struggle to dynamically adjust signal coverage based on real-time changes in terrain, buildings, and user distribution, easily leading to coverage blind spots. In capacity optimization, frequency resource allocation is inflexible when facing a large number of users accessing the network during peak hours, resulting in insufficient network capacity. In interference optimization, the handling of co-channel and adjacent-channel interference is not intelligent enough, affecting network quality. In user experience optimization, they cannot accurately schedule signals according to the different service needs of users, reducing user satisfaction.

[0004] Therefore, developing an algorithm that can comprehensively consider multiple factors and achieve dynamic and intelligent signal scheduling is of great significance for improving the performance of 5G base stations and meeting diverse business needs.

[0005] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0006] In view of the problems in related technologies, this invention proposes a signal scheduling method based on 5G base stations to overcome the above-mentioned technical problems existing in the existing related technologies.

[0007] The technical solution of this invention is implemented as follows:

[0008] A signal scheduling method based on 5G base stations includes the following steps:

[0009] Pre-collection of data includes: real-time collection of user equipment data, network status data, and environmental parameters through the base station's built-in sensors and network monitoring unit;

[0010] The collected data is preprocessed, including cleaning, deduplication and normalization of the collected data, and transforming non-standardized parameters to the [0,1] interval through mapping formula;

[0011] Based on the preprocessed data, an intelligent scheduling model is constructed using a convolutional neural network, which includes calibrating an objective function that includes coverage quality indicators, resource utilization, interference suppression indicators, and user experience indicators.

[0012] Dynamic scheduling decisions are made, including intelligent scheduling models that generate signal scheduling decisions based on real-time input data.

[0013] Furthermore, the user equipment data includes at least the number of users N and location coordinates (x, y, y). i ,y i Business Type S i (i = 1, 2, ..., N) and signal received power RSRP i The network status data includes at least: a set of available frequency resources F = {f1, f2, ..., f...} M Channel occupancy rate O j and interference power I j (j=1,2,...,M); the environmental parameters include at least: path loss factor α, shadow fading standard deviation σ, and obstacle attenuation coefficient β.

[0014] Furthermore, the objective function is expressed as:

[0015] maxJ=ω1J1+ω2J2+ω3J3+ω4J4;

[0016] Wherein, J1 is the coverage quality indicator, J2 is the resource utilization rate, J3 is the interference suppression indicator, and J4 is the user experience indicator, and ω1, ω2, ω3, and ω4 are weighting coefficients.

[0017] Furthermore, the coverage quality index J1 is expressed as:

[0018]

[0019] Where N is the number of user equipment, RSRP i Let RSRP be the signal received power of the i-th user equipment. th This is the minimum received power threshold.

[0020] Furthermore, the resource utilization rate J2 is expressed as:

[0021]

[0022] Among them, O j Let B be the occupancy rate of the j-th channel. j Let be the bandwidth of channel j.

[0023] Furthermore, the interference suppression index J3 is expressed as:

[0024]

[0025] Where M is the total number of channels, I j Let P be the interference power of the j-th channel. max This is the maximum transmission power.

[0026] Furthermore, the user experience metric J4 is represented as:

[0027]

[0028] Among them, TP i TP represents the actual throughput of the i-th user device. req,i Let be the throughput required by the service of the i-th user device.

[0029] Furthermore, the scheduling decision includes at least frequency resource allocation, transmission power adjustment, and channel selection.

[0030] The beneficial effects of this invention are:

[0031] This invention achieves dynamic optimization of 5G base station signal resources by constructing a multi-dimensional data-driven intelligent scheduling model. It integrates environmental parameters such as path loss factor and shadow fading standard deviation with user service characteristics, and through a multi-objective optimization function, it synergistically improves coverage quality, resource utilization, interference suppression, and user experience, overcoming the limitations of traditional static scheduling models in complex scenarios. Based on a deep reinforcement learning-based decision-making mechanism, it can perceive network state changes in real time and generate optimal scheduling strategies, ensuring both the QoS requirements of high-priority services and the refined utilization of spectrum resources. This allows base stations to maintain stable and efficient operation even in scenarios with high-density user access and diverse mixed service support, significantly enhancing the resilience and adaptability of 5G networks.

[0032] Furthermore, by introducing closed-loop feedback, a continuously optimized dynamic adjustment capability is formed, enabling base station signal scheduling to adaptively adjust to changes in the environment, service distribution, and user needs. This effectively solves problems such as the coexistence of coverage blind spots and interference, and the mismatch between resource allocation and service requirements in traditional scheduling. Simultaneously, the algorithm's differentiated support capabilities for multiple service types, including eMBB, uRLLC, and mMTC, provide key technical support for the large-scale application of 5G networks across various industries, driving the upgrade of network services from "general adaptation" to "precise customization," and laying the foundation for the intelligent evolution of future mobile communication networks. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0034] Figure 1 This is a flowchart illustrating a signal scheduling method based on a 5G base station according to an embodiment of the present invention. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0036] According to an embodiment of the present invention, a signal scheduling method based on a 5G base station is provided.

[0037] like Figure 1 As shown, the signal scheduling method based on a 5G base station according to an embodiment of the present invention includes the following steps:

[0038] Step S1, pre-collection of data, including: real-time collection of user equipment data, network status data and environmental parameters through the base station's built-in sensors and network monitoring unit;

[0039] The user equipment data includes at least the number of users N and location coordinates (x, y). i ,y i Business Type S i (i = 1, 2, ..., N) and signal received power RSRP i ;

[0040] The network status data includes at least: an available frequency resource set F = {f1, f2, ..., f...} M Channel occupancy rate O j and interference power I j (j = 1, 2, ..., M);

[0041] The environmental parameters include at least: path loss factor α, shadow fading standard deviation σ, and obstacle attenuation coefficient β.

[0042] Step S2 involves preprocessing the collected data, including outlier handling and normalization. Outlier handling can be performed using the 3σ criterion to remove outlier RSRP data. Non-standardized parameters are then mapped to the [0,1] interval.

[0043] Step S3: Based on the preprocessed data, construct an intelligent scheduling model using a convolutional neural network. This includes defining an objective function that includes coverage quality metrics, resource utilization, interference suppression metrics, and user experience metrics, expressed as:

[0044] maxJ=ω1J1+ω2J2+ω3J3+ω4J4;

[0045] Where J1 is the coverage quality index, expressed as:

[0046]

[0047] Among them, RSRP th The sigmoid function achieves a smooth transition by setting the minimum received power threshold;

[0048] Where J2 is the resource utilization rate, expressed as:

[0049]

[0050] Among them, B j Let be the bandwidth of channel j;

[0051] Wherein, J3 is the interference suppression index, expressed as:

[0052]

[0053] Among them, P max This is the maximum transmission power;

[0054] Where J4 is the user experience metric, expressed as:

[0055]

[0056] Among them, TP i For actual throughput, TP req,i The throughput is determined by business requirements, with a weighting coefficient ω1+ω2+ω3+ω4=1, which is dynamically adjusted according to business priority.

[0057] Step S4 involves making dynamic scheduling decisions, including the intelligent scheduling model generating signal scheduling decisions based on real-time input data, as detailed below:

[0058] Frequency resource allocation includes dynamically allocating frequency resources based on the service type and quantity of user equipment, prioritizing the allocation of more frequency resources for services with high bandwidth requirements (such as high-definition video transmission);

[0059] Transmission power adjustments are made based on the location of user equipment, signal strength, and environmental data including terrain and building distribution. For areas with weak signals, transmission power is appropriately increased to expand coverage; for areas with strong signals and high user density, transmission power is reasonably reduced to minimize interference.

[0060] Channel selection is performed by analyzing channel occupancy and interference signal strength to select the channel with the least interference for communication with user equipment.

[0061] In addition, when applied, the system also includes: the base station executes signal scheduling operations based on the generated scheduling decisions, and monitors the network performance data after scheduling in real time, such as coverage, capacity, interference level, user experience indicators, etc., and feeds this data back to the intelligent scheduling model, dynamically updating the model parameters based on the real-time performance data.

[0062] The above technical solution was applied to 5G base station signal scheduling in a city's commercial area, and the specific implementation is as follows:

[0063] The 5G base station pre-deploys sensors and network monitoring modules to collect the following data in real time: User equipment data: The number of user equipment in the coverage area is counted every 5 minutes, the location of user equipment is obtained through GPS positioning, the user's service type is identified, and the signal reception strength of user equipment is monitored; Base station operation data: The base station's transmission power, the occupancy rate of each channel, and the usage of frequency resources are monitored in real time; Environmental data: The terrain of this commercial area is flat with dense buildings, including many high-rise buildings, and the strength and source of interference signals generated by other base stations and electronic devices in the surrounding area are monitored in real time.

[0064] Data preprocessing is performed on the collected data, including: processing the collected data to remove abnormal signal reception strength data caused by equipment failure and duplicate user equipment location information, and normalizing data such as the number of user equipment and signal strength to the range of [0,1].

[0065] A smart scheduling model is constructed, including training the preprocessed data using a convolutional neural network. The model's input is the preprocessed multi-dimensional data, and its output includes a frequency resource allocation scheme, transmission power adjustment values, and channel selection results. The objective function is set as follows: while maximizing coverage, achieving network capacity utilization of over 90%, interference signal strength below -100dBm, and a user satisfaction score of 4.5 out of 5.

[0066] Dynamic scheduling decisions: During the morning peak hours on weekdays (8:00-10:00), the number of user devices in this business district increases sharply, with video calls and file transfers accounting for a large proportion. The intelligent scheduling model makes decisions based on real-time data: allocating 30% of the 2.6GHz band frequency resources to video call services and 20% to file transfer services; increasing base station transmission power by 10% in areas obstructed by tall buildings; and selecting channels with interference signal strength below -110dBm to provide service to user devices.

[0067] Scheduling Execution and Feedback: After the base station executes the scheduling decision, real-time monitoring shows that the coverage area has expanded by 5%, the network capacity utilization rate has reached 92%, the average interference signal strength is -105dBm, and the user satisfaction score obtained through user feedback surveys is 4.7. This data is fed back to the intelligent scheduling model, which fine-tunes its internal parameters based on the feedback results to adapt to subsequent network changes.

[0068] Through the application of this embodiment, the 5G network performance in the commercial area has been significantly improved, effectively meeting the business needs during peak hours and enhancing the user experience.

[0069] In summary, by employing the above-described technical solution of the present invention, the following effects can be achieved:

[0070] This invention achieves dynamic optimization of 5G base station signal resources by constructing a multi-dimensional data-driven intelligent scheduling model. It integrates environmental parameters such as path loss factor and shadow fading standard deviation with user service characteristics, and through a multi-objective optimization function, it synergistically improves coverage quality, resource utilization, interference suppression, and user experience, overcoming the limitations of traditional static scheduling models in complex scenarios. Based on a deep reinforcement learning-based decision-making mechanism, it can perceive network state changes in real time and generate optimal scheduling strategies, ensuring both the QoS requirements of high-priority services and the refined utilization of spectrum resources. This allows base stations to maintain stable and efficient operation even in scenarios with high-density user access and diverse mixed service support, significantly enhancing the resilience and adaptability of 5G networks.

[0071] Furthermore, by introducing closed-loop feedback, a continuously optimized dynamic adjustment capability is formed, enabling base station signal scheduling to adaptively adjust to changes in the environment, service distribution, and user needs. This effectively solves problems such as the coexistence of coverage blind spots and interference, and the mismatch between resource allocation and service requirements in traditional scheduling. Simultaneously, the algorithm's differentiated support capabilities for multiple service types, including eMBB, uRLLC, and mMTC, provide key technical support for the large-scale application of 5G networks across various industries, driving the upgrade of network services from "general adaptation" to "precise customization," and laying the foundation for the intelligent evolution of future mobile communication networks.

[0072] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Those skilled in the art, upon considering the disclosure in the specification and embodiments, will readily conceive of other embodiments of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0073] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for signal scheduling based on a 5G base station, characterized in that, The method comprises the following steps: Pre-acquisition of data, including: through the base station built-in sensor and network monitoring unit, real-time acquisition of user equipment data, network state data and environmental parameters; Pretreatment of the collected data, including: cleaning, deduplication and normalization processing of the collected data, and conversion of non-standardized parameters to the [0, 1] interval through a mapping formula; Based on the pretreated data, an intelligent scheduling model is constructed using a convolutional neural network, which includes a target function calibrated to include coverage quality indicators, resource utilization, interference suppression indicators and user experience indicators; Dynamic scheduling decision, including the intelligent scheduling model generating signal scheduling decisions according to real-time input data.

2. The 5G base station-based signal scheduling method according to claim 1, characterized in that, The user equipment data at least includes user quantity N, position coordinate (x i ,y i ), service type S i (i=1,2,...,N) and signal receiving power RSRP i ; The network status data includes at least: an available frequency resource set F = {f1, f2, ..., f...} M Channel occupancy rate O j and interference power I j (j=1,2,...,M); the environmental parameters include at least: path loss factor α, shadow fading standard deviation σ, and obstacle attenuation coefficient β. 3.The 5G base station based signal scheduling method according to claim 1, wherein, The target function is expressed as: max J = ω1J1 + ω2J2 + ω3J3 + ω4J4; Wherein, J1 is the coverage quality indicator, J2 is the resource utilization, J3 is the interference suppression indicator and J4 is the user experience indicator, ω1, ω2, ω3, ω4 are weight coefficients.

4. The method of claim 3, wherein, The coverage quality indicator J1 is expressed as: wherein N is the number of user equipments, RSRP i is the signal received power of the i-th user equipment, RSRP th is the minimum received power threshold.

5. The method of claim 4, wherein, The resource utilization J2 is expressed as: where O j is the occupancy of the jth channel, B j is the bandwidth of channel j. 6.The 5G base station based signal scheduling method according to claim 1, wherein, The interference suppression indicator J3 is expressed as: where M is the total number of channels, I j is the interference power of the jth channel, P max is the maximum transmit power. 7.The 5G base station based signal scheduling method according to claim 6, characterized in that, The user experience indicator J4 is expressed as: wherein TP i is the actual throughput of the i-th user equipment, TP req,i is the traffic demand throughput of the i-th user equipment. 8.The 5G base station based signal scheduling method according to claim 1, wherein, The scheduling decision at least includes frequency resource allocation, transmission power adjustment and channel selection.

Images