Efficient spectrum resource allocation method and system in electric power communication

Abstract

The invention relates to the technical field of electric power system communication, in particular to an efficient spectrum resource allocation method and system in electric power communication, and the method comprises the steps: carrying out quantitative modeling on electric power communication services, dividing service types, defining key parameters, and predicting service demand fluctuation in a future time period; the method comprises the following steps: deploying spectrum sensors at an electric power communication base station and a key terminal in real time to obtain state information of each frequency band, and collecting parameters to construct a spectrum quality matrix; based on the business demand model and the frequency spectrum state, a multi-objective optimization algorithm is adopted to generate an optimal allocation scheme, a mathematical model containing business demands, frequency spectrum resources and interference avoidance constraints is established, and a frequency band allocation scheme and power control parameters are output; and executing an allocation strategy, feeding back optimization model parameters according to an actual communication effect, dynamically adjusting spectrum allocation, and optimizing the parameters. According to the invention, efficient allocation of spectrum resources is realized, and the spectrum utilization rate and the key service guarantee rate are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system communications, and relates to a method and system for efficiently allocating spectrum resources in power communications. Background Art

[0002] In current power communication networks, spectrum resource allocation primarily relies on static allocation or fixed rule-based allocation. Static allocation methods pre-set spectrum resource partitioning schemes based on historical traffic volume, allocating fixed frequency bands to specific communication services (such as relay protection and remote meter reading). These methods lack the ability to perceive real-time network status and changes in service demand. Some solutions employ priority-based static scheduling strategies, pre-setting resource allocation priorities based solely on service type. These strategies are unable to adapt to complex scenarios such as real-time data flow fluctuations and dynamic network topology changes (such as the entry and exit of distribution automation terminals) in power communication networks.

[0003] Existing technologies typically rely on the experience of network planners to set allocation parameters, failing to fully consider the specific characteristics of power communication services (such as the stringent latency requirements of relay protection services and the bursty data transmission needs of distribution network automation services). Furthermore, traditional methods fail to model the correlation between spectrum resources and power service characteristics, making it difficult to quantitatively assess the impact of spectrum allocation on power system security and reliability.

[0004] Existing technologies suffer from the following shortcomings: low spectrum utilization and a static allocation model that fails to respond to the dynamic changes in power communication services, resulting in some frequency bands being idle during low-load periods and insufficient spectrum resources during high-load periods. For example, during off-peak periods, bandwidth requirements for remote meter reading services decrease, but the pre-set frequency bands remain occupied, resulting in wasted resources. Service assurance capabilities are insufficient, as they fail to prioritize power communication services and prioritize reliability requirements. When spectrum resources are limited, critical services (such as relay protection) may experience transmission delays due to insufficient resource allocation, impacting the safe and stable operation of the power system. Traditional methods lack interference mitigation capabilities: They fail to consider the impact of electromagnetic interference (such as electromagnetic radiation from substation equipment and industrial noise) in the power communication environment on spectrum quality and lack a dynamic spectrum adjustment mechanism for interference mitigation, resulting in unstable communication link quality. Furthermore, they lack intelligent optimization mechanisms and rely on manual experience to set allocation strategies. This makes them unable to adapt to the massive number of terminal accesses and diverse service types in smart grids, making it difficult to achieve globally optimal spectrum resource allocation.

[0005] Therefore, there is an urgent need for an efficient spectrum resource allocation method and system in power communication to solve the above technical problems. Summary of the Invention

[0006] The present invention provides a method and system for efficient spectrum resource allocation in electric power communications, which overcomes the deficiencies of the above-mentioned prior art and can effectively solve the problems of low spectrum resource allocation efficiency, insufficient key business guarantee and weak system anti-interference capability in electric power communications.

[0007] One of the technical solutions of the present invention is achieved through the following measures: A method for efficient spectrum resource allocation in power communication, comprising the following steps: Step S1: quantitatively model the power communication service, classify the service types and define key parameters, and predict the service demand fluctuations in the future period based on historical service data; Step S2: Acquire status information of each frequency band in real time, collect parameters and construct a spectrum quality matrix; Step S3: Based on the service demand model and spectrum status, a multi-objective optimization algorithm combined with deep reinforcement learning is used to generate an optimal allocation plan, a mathematical model including service demand, spectrum resources, and interference avoidance constraints is established, and the frequency band allocation plan and power control parameters are output; Step S4: Execute the allocation strategy, optimize the model parameters according to the actual communication effect feedback, dynamically adjust the spectrum allocation, and optimize the parameters.

[0008] The following is a further optimization and / or improvement of one of the above-mentioned technical solutions: The multi-objective optimization algorithm in the above step S3 takes maximizing spectrum utilization, guaranteeing key services, and anti-interference capability of the system as optimization goals.

[0009] The key parameters in the above step S1 may include a bandwidth threshold and a maximum allowable delay, wherein the bandwidth threshold for real-time services is ≥2 Mbps, and the maximum allowable delay for relay protection services is ≤5 ms.

[0010] When predicting business demand fluctuations in future periods based on historical business data in the above step S1, the time series analysis method used can be an LSTM neural network, and the historical business data is the minute-level business traffic in the past month.

[0011] In the above step S2, spectrum sensors are deployed at power communication base stations and key terminals to obtain status information of each frequency band.

[0012] The spectrum allocation algorithm combined with deep reinforcement learning in the above step S3 can be a spectrum allocation algorithm based on deep deterministic policy gradient, which takes the spectrum state matrix and the service demand vector as input.

[0013] The above spectrum allocation algorithm based on deep deterministic policy gradient is trained interactively with the power communication network environment to make the algorithm adaptive to the dynamic changes of the power system.

[0014] The spectrum state matrix may include the occupancy rate, interference power spectrum density and channel fading characteristic parameters of each frequency band, and the service demand vector may include the bandwidth requirement, delay sensitivity and reliability index parameters of each service.

[0015] The second technical solution of the present invention is achieved through the following measures: an efficient spectrum resource allocation system in power communication, comprising: The power business characteristic modeling module is used to classify power communication services, define key parameters, and predict business demand fluctuations in future periods based on historical business data; The spectrum status perception module is used to obtain the occupancy rate and interference intensity of each frequency band in real time, collect parameters and build a spectrum quality matrix; The intelligent optimization allocation module generates the optimal allocation plan based on the service demand model and spectrum status using a multi-objective optimization algorithm combined with deep reinforcement learning. It establishes a mathematical model that includes service demand, spectrum resources, and interference avoidance constraints, and outputs the frequency band allocation plan and power control parameters. The resource control and feedback module is used to execute allocation strategies, optimize model parameters based on actual communication effect feedback, and dynamically adjust spectrum allocation.

[0016] The following is a further optimization and / or improvement of the second technical solution of the above invention: The efficient spectrum resource allocation system in the electric power communication may further include: The data collection layer may include spectrum sensors and service flow monitoring equipment to collect spectrum status and service data in real time; The data processing layer may include edge computing nodes and central servers to complete data preprocessing, business modeling and optimization calculations; The control execution layer may include a software-defined network controller and radio frequency front-end equipment to achieve dynamic allocation and adjustment of spectrum resources; The application management layer provides a human-computer interaction interface to support operation and maintenance personnel in configuring business priorities, viewing resource usage status and system optimization effects.

[0017] This invention proposes a highly efficient spectrum resource allocation method and system for power communication, significantly improving the efficiency and reliability of spectrum resource utilization in power communication networks. By quantitatively modeling power communication services, accurately classifying service types and defining key parameters, and combining historical service data to predict future service demand fluctuations, this method provides data support for proactive spectrum resource allocation. Spectrum sensors deployed at power communication base stations and key terminals acquire real-time status information for each frequency band and construct a spectrum quality matrix, ensuring dynamic monitoring and assessment of spectrum resources. A multi-objective optimization algorithm combined with deep reinforcement learning comprehensively considers objectives such as maximizing spectrum utilization, ensuring key service availability, and system anti-interference capability to generate an optimal allocation plan, effectively addressing the low resource utilization and uneven service assurance inherent in traditional spectrum allocation methods. The spectrum allocation algorithm, based on deep deterministic policy gradients, is interactively trained with the power communication network environment, enabling it to adapt to dynamic changes in the power system, further enhancing its flexibility and adaptability. Through multi-dimensional optimization, this invention comprehensively improves the spectrum resource management capabilities of the power communication system, enhancing the system's adaptability to diverse service demands and anti-interference capabilities, and providing a strong guarantee for the efficient and stable operation of the power communication network. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Attachment Figure 1 Schematic diagram of a flow chart of a method for efficient spectrum resource allocation in power communication according to an embodiment of the present invention.

[0019] Attachment Figure 2 Schematic diagram of the structure of a system for efficient spectrum resource allocation in power communication according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention is not limited to the following embodiments, and specific implementation methods can be determined based on the technical solutions of the present invention and actual conditions.

[0021] The present invention will be further described below in conjunction with the embodiments: Example 1: As shown in the attached Figure 1 As shown, the efficient spectrum resource allocation method in power communication includes the following steps: Step S1: quantitatively model the power communication service, classify the service types and define key parameters, and predict the service demand fluctuations in the future period based on historical service data; Step S2: Acquire status information of each frequency band in real time, collect parameters and construct a spectrum quality matrix; Step S3: Based on the service demand model and spectrum status, a multi-objective optimization algorithm combined with deep reinforcement learning is used to generate an optimal allocation plan, a mathematical model including service demand, spectrum resources, and interference avoidance constraints is established, and the frequency band allocation plan and power control parameters are output; Step S4: Execute the allocation strategy, optimize the model parameters according to the actual communication effect feedback, dynamically adjust the spectrum allocation, and optimize the parameters.

[0022] By first modeling services and forecasting demand, we can identify the characteristics of different services and future demand changes, providing a basis for resource allocation. We then monitor spectrum status in real time and construct a quality matrix to reflect the availability of each frequency band. We then utilize a multi-objective optimization algorithm based on deep reinforcement learning to generate the optimal solution while satisfying multiple constraints. Finally, we continuously optimize through execution and feedback, achieving dynamic adjustments. This approach allows spectrum allocation to better align with actual service needs, improving allocation accuracy and flexibility while also dynamically adapting to changes in services and spectrum.

[0023] In this embodiment, the multi-objective optimization algorithm in step S3 optimizes spectrum utilization, critical service assurance, and system anti-interference capabilities. By integrating these three objectives into the algorithm, the algorithm not only focuses on overall resource utilization efficiency when searching for the optimal allocation solution, but also prioritizes the communication needs of critical services and enhances the system's ability to cope with interference, achieving a multi-dimensional balanced optimization. This avoids resource waste or insufficient service assurance caused by single-objective optimization, thereby improving the overall system performance.

[0024] In this embodiment, the key parameters in step S1 may include bandwidth thresholds and maximum allowable latency. The bandwidth threshold for real-time services is ≥2 Mbps, and the maximum allowable latency for relay protection services is ≤5 ms. By defining the key parameters for different services, this provides specific standards for service modeling, enabling subsequent demand forecasting and resource allocation to accurately match the core requirements of the service, especially for services with high real-time and reliability requirements. This ensures that critical services receive sufficient resource support, meet their basic operating requirements, and improve the stability of service operations.

[0025] In this embodiment, in step S1, when predicting future service demand fluctuations based on historical service data, the time series analysis method employed may be an LSTM neural network. The historical service data consists of minute-by-minute service traffic over the past month. By learning from historical service data, the LSTM neural network captures the time series characteristics and fluctuation patterns of service demand, thereby predicting future demand and providing data support for pre-emptive spectrum resource allocation planning. This improves the accuracy of demand forecasts, makes spectrum allocation more forward-looking, and reduces imbalances between resource supply and demand.

[0026] In this embodiment, step S2 involves deploying spectrum sensors at power communication base stations and key terminals to obtain status information for each frequency band. By deploying spectrum sensors at key locations, real-time information on occupancy and interference, such as for each frequency band, is collected. This ensures comprehensive and timely spectrum data, laying the foundation for constructing an accurate spectrum quality matrix. This allows for real-time monitoring of the dynamic changes in spectrum resources, providing a reliable basis for subsequent optimized allocation and improving the adaptability of allocation plans.

[0027] In this embodiment, the spectrum allocation algorithm incorporating deep reinforcement learning in step S3 can be a spectrum allocation algorithm based on deep deterministic policy gradients, taking the spectrum state matrix and the service demand vector as input. By learning the spectrum state and service demand through a deep deterministic policy gradient algorithm, it can generate a deterministic optimal allocation strategy within the continuous spectrum resource space and directly output specific frequency band allocation and power control parameters. This improves the decision-making efficiency and accuracy of the spectrum allocation algorithm, making the allocation plan more tailored to actual spectrum and service conditions.

[0028] In this embodiment, a spectrum allocation algorithm based on deep deterministic policy gradients (DDPGs) is trained interactively with the power communication network environment, enabling it to adapt to the dynamic changes in the power system. Through continuous interaction with the network environment, the algorithm continuously learns about environmental changes and the characteristics of service demand fluctuations, adjusting its decision model to adapt to the dynamic changes in spectrum status and service demand in the power system. This enhances the algorithm's flexibility and adaptability, ensuring that the optimal allocation plan can be generated even when the system state changes.

[0029] In this embodiment, the spectrum state matrix may include the occupancy rate, interference power spectrum density, and channel fading characteristic parameters for each frequency band, while the service demand vector may include the bandwidth requirements, delay sensitivity, and reliability index parameters for each service. By incorporating multi-dimensional parameters into the spectrum state matrix and service demand vector, the algorithm comprehensively reflects the quality of spectrum resources and the specific needs of services. This allows the algorithm to comprehensively consider multiple factors during the optimization process and generate a more comprehensive allocation plan. This improves the rationality and targetedness of the allocation plan, better balancing spectrum resource utilization and service needs.

[0030] This invention constructs a dynamic spectrum allocation model that integrates the characteristics of power communication services, achieving precise matching of spectrum resources with service requirements and improving resource utilization. It also designs an adaptive allocation algorithm based on service priority to ensure communication quality for critical services while improving resource utilization efficiency for non-critical services. It also establishes a real-time spectrum status perception and interference avoidance mechanism, dynamically adjusting allocation strategies to cope with complex electromagnetic environments. By quantitatively analyzing the characteristics of power communication services and spectrum usage patterns, it achieves global optimal allocation of spectrum resources.

[0031] This paper proposes a closed-loop spectrum resource allocation method based on "perception-modeling-optimization-control." This method achieves efficient spectrum resource utilization by integrating power service characteristic analysis, real-time spectrum status perception, and intelligent optimization algorithms. This method first establishes a database of power communication service characteristics and quantitatively models the bandwidth requirements, latency sensitivity, and reliability indicators of different service types (such as relay protection, distribution network automation, and electricity consumption information collection). Secondly, a spectrum sensing module acquires real-time status information such as occupancy and interference intensity for each frequency band. Then, based on the service demand model and spectrum status, an improved multi-objective optimization algorithm (such as a spectrum allocation algorithm combined with deep reinforcement learning) is used to generate the optimal allocation plan. Finally, a resource control module executes the allocation strategy and optimizes model parameters based on actual communication performance feedback, forming a closed-loop optimization mechanism.

[0032] The present invention integrates the dynamic modeling method of the characteristics of the power business, innovatively combines the priority, latency requirements and other characteristics of the power business with the spectrum allocation model, establishes a business demand-spectrum resource mapping relationship, and breaks through the allocation model that only considers bandwidth requirements in the traditional communication field. The present invention is based on the intelligent optimization algorithm of deep reinforcement learning, and introduces the DDPG framework to achieve adaptive optimization of spectrum allocation, so that the system can adapt to the dynamic changes of the power communication network through autonomous learning without prior knowledge, thereby improving the intelligence level of the allocation strategy. The present invention proposes an anti-interference allocation mechanism under multi-dimensional constraints, introduces spectrum interference characteristic parameters into the optimization model, and reduces the impact of electromagnetic interference on power communications through power control and frequency band avoidance strategies, thereby ensuring the reliability of key services.

[0033] Compared with the existing technology, the present invention has the following advantages: (1) Significant improvement in spectrum utilization: By dynamically adapting to business needs, spectrum utilization can be increased by more than 30% compared with the traditional static allocation method, especially in scenarios with large business fluctuations (such as burst data transmission during fault repair of distribution automation system). (2) Enhanced key business guarantee capability: For real-time services such as relay protection, the priority-driven resource reservation mechanism can increase the service delay compliance rate from 95% of the traditional method to more than 99.9%, meeting the safe operation requirements of the power system. (3) Improved anti-interference capability: Through real-time spectrum sensing and interference avoidance algorithms, the system's communication bit error rate in electromagnetic interference environments can be reduced by 50%, ensuring the stability of the power communication link. (4) High level of intelligence: Without manual intervention, the system can autonomously learn the power business model and spectrum usage rules, adapt to the development trend of the increasing number of terminals and diversified business types in the smart grid, and reduce operation and maintenance costs.

[0034] Example 2: As shown in the attached Figure 2 As shown, this embodiment provides an efficient spectrum resource allocation system in power communication, including: The power business characteristic modeling module is used to classify power communication services, define key parameters, and predict business demand fluctuations in future periods based on historical business data; it divides power communication services into real-time (relay protection, fault location), quasi-real-time (distribution network automation), and non-real-time (power consumption information collection, video monitoring), and defines key parameters for each type of service, such as bandwidth threshold (real-time service ≥ 2Mbps), maximum allowable delay (relay protection ≤ 5ms), bit error rate requirement (≤ 10⁻ 6 Based on historical service data (e.g., minute-level service traffic over the past month), time series analysis (e.g., LSTM neural networks) is used to predict service demand fluctuations in future periods and capture the surge in service volume during peak electricity consumption periods (e.g., morning and evening peaks).

[0035] The spectrum status perception module is used to obtain real-time occupancy and interference intensity for each frequency band, collect parameters, and construct a spectrum quality matrix. This module collects parameters such as spectrum occupancy (the probability of a frequency band being occupied per unit time), interference power spectral density (a measure of electromagnetic interference intensity), and channel fading characteristics (such as signal attenuation caused by multipath effects) to construct the spectrum quality matrix. Spectrum sensors are deployed at power communication base stations and key terminals. Edge computing nodes preprocess the perception data, reducing the computing pressure on central nodes and improving real-time perception.

[0036] The intelligent optimization allocation module is used to generate the optimal allocation plan based on the business demand model and spectrum status, using a multi-objective optimization algorithm combined with deep reinforcement learning, establish a mathematical model containing business demand, spectrum resources, and interference avoidance constraints, and output frequency band allocation plans and power control parameters; with the goal of maximizing spectrum utilization, ensuring key business guarantees (such as relay protection business delay compliance rate ≥ 99.9%), and system anti-interference capability (average bit error rate ≤ 10⁻ 5 ) as the optimization objective, a mathematical model was established that incorporates service demand constraints, spectrum resource constraints, and interference avoidance constraints. A spectrum allocation algorithm based on DDPG (Deep Deterministic Policy Gradient) was designed. This algorithm takes the spectrum state matrix and service demand vector as input and outputs frequency band allocation plans and power control parameters for each service. Through interactive training with the environment (the power communication network), the algorithm adapts to the dynamic changes of the power system.

[0037] The resource control and feedback module executes allocation strategies and optimizes model parameters based on actual communication performance feedback, dynamically adjusting spectrum allocation. Based on the optimization algorithm's output, the software-defined network (SDN) controller dynamically adjusts spectrum allocation for each service, enabling real-time switching of frequency bands and resource reconfiguration. Actual communication metrics (such as service latency, bandwidth utilization, and bit error rate) are collected and compared with model predictions. Gradient descent is used to optimize the parameters of the demand forecasting model and optimization algorithm, improving system adaptability.

[0038] This invention forms a complete spectrum resource allocation closed loop through the collaborative work of various modules: the power service characteristics modeling module provides service requirements, the spectrum status perception module provides spectrum status data, the intelligent optimization allocation module generates the optimal solution, and the resource control and feedback module executes and optimizes the strategy. This enables full process management from service analysis to solution execution and optimization and adjustment, improving the overall operational efficiency of the system.

[0039] In this embodiment, the efficient spectrum resource allocation system in electric power communication may further include: The data collection layer may include spectrum sensors and service flow monitoring equipment to collect spectrum status and service data in real time; The data processing layer may include edge computing nodes and central servers to complete data preprocessing, business modeling and optimization calculations; The control execution layer may include a software-defined network controller and radio frequency front-end equipment to achieve dynamic allocation and adjustment of spectrum resources; The application management layer provides a human-computer interaction interface to support operation and maintenance personnel in configuring business priorities, viewing resource usage status and system optimization effects.

[0040] The present invention adopts a layered architecture design. The data acquisition layer obtains raw data, the data processing layer performs data processing and calculation, the control execution layer implements the allocation strategy, and the application management layer provides human-computer interaction. Each layer collaborates to complete the full-process management of spectrum resources. In this way, the modularity and maintainability of the system can be improved, operation and maintenance management can be facilitated, and the efficiency of data processing and strategy execution can be ensured. When working, the business is first modeled and demand forecasted through the power business characteristic modeling module. The spectrum state perception module obtains the spectrum state in real time and constructs a matrix; the intelligent optimization allocation module combines the two and uses the multi-objective optimization algorithm of deep reinforcement learning to generate an allocation plan; the resource control and feedback module executes the plan and optimizes parameters based on feedback. The overall efficient allocation of spectrum resources is achieved, the utilization rate, business guarantee capability and system anti-interference ability are improved, and the stable operation of power communications is ensured.

[0041] The above technical features constitute the embodiments of the present invention, which have strong adaptability and implementation effect. Non-essential technical features can be added or removed according to actual needs to meet the requirements of different situations.

Claims

1. An efficient spectrum resource allocation method in power communication, characterized in that: The following steps are involved: Step S1: quantitatively model the power communication service, classify the service types and define key parameters, and predict the service demand fluctuations in the future period based on historical service data; Step S2: Acquire status information of each frequency band in real time, collect parameters and construct a spectrum quality matrix; Step S3: Based on the service demand model and spectrum status, a multi-objective optimization algorithm combined with deep reinforcement learning is used to generate an optimal allocation plan, a mathematical model including service demand, spectrum resources, and interference avoidance constraints is established, and the frequency band allocation plan and power control parameters are output; Step S4: Execute the allocation strategy, optimize the model parameters according to the actual communication effect feedback, dynamically adjust the spectrum allocation, and optimize the parameters.

2. The efficient spectrum resource allocation method in electric power communication according to claim 1, characterized in that: The multi-objective optimization algorithm in step S3 takes maximizing spectrum utilization, guaranteeing key services, and anti-interference capability of the system as optimization goals.

3. The efficient spectrum resource allocation method in electric power communication according to claim 1 or 2, characterized in that: The key parameters in step S1 include bandwidth threshold and maximum allowable delay, where the bandwidth threshold for real-time services is ≥2Mbps and the maximum allowable delay for relay protection services is ≤5ms.

4. The efficient spectrum resource allocation method in electric power communication according to claim 1 or 2, characterized in that: In step S1, when predicting business demand fluctuations in future time periods based on historical business data, the time series analysis method used is the LSTM neural network, and the historical business data is the minute-level business traffic in the past month.

5. The efficient spectrum resource allocation method in electric power communication according to claim 1 or 2, characterized in that: In step S2, spectrum sensors are deployed at power communication base stations and key terminals to obtain status information of each frequency band.

6. The efficient spectrum resource allocation method in electric power communication according to claim 1 or 2, characterized in that: The spectrum allocation algorithm combined with deep reinforcement learning in step S3 is a spectrum allocation algorithm based on deep deterministic policy gradient, which takes the spectrum state matrix and the service demand vector as input.

7. The efficient spectrum resource allocation method in electric power communication according to claim 6, characterized in that: The spectrum allocation algorithm based on deep deterministic policy gradient is trained interactively with the power communication network environment to make the algorithm adaptive to the dynamic changes of the power system.

8. The efficient spectrum resource allocation method in electric power communication according to claim 6, characterized in that: The spectrum state matrix includes the occupancy rate, interference power spectrum density and channel fading characteristic parameters of each frequency band, and the service demand vector includes the bandwidth requirement, delay sensitivity and reliability index parameters of each service.

9. An efficient spectrum resource allocation system in power communication, characterized in that: include: The power business characteristic modeling module is used to classify power communication services, define key parameters, and predict business demand fluctuations in future periods based on historical business data; The spectrum status perception module is used to obtain the occupancy rate and interference intensity of each frequency band in real time, collect parameters and build a spectrum quality matrix; The intelligent optimization allocation module generates the optimal allocation plan based on the service demand model and spectrum status using a multi-objective optimization algorithm combined with deep reinforcement learning. It establishes a mathematical model that includes service demand, spectrum resources, and interference avoidance constraints, and outputs the frequency band allocation plan and power control parameters. The resource control and feedback module is used to execute allocation strategies, optimize model parameters based on actual communication effect feedback, and dynamically adjust spectrum allocation.

10. The efficient spectrum resource allocation system in electric power communication according to claim 9, characterized in that: Also includes: The data collection layer includes spectrum sensors and service traffic monitoring equipment, which are used to collect spectrum status and service data in real time; The data processing layer includes edge computing nodes and central servers, which are used to complete data preprocessing, business modeling and optimization calculations; The control execution layer, including the software-defined network controller and radio frequency front-end equipment, is used to realize the dynamic allocation and adjustment of spectrum resources; The application management layer provides a human-computer interaction interface to support operation and maintenance personnel in configuring business priorities, viewing resource usage status and system optimization effects.

Images