A power business dispatching method and system based on 5G communication hierarchical classification

Abstract

This invention discloses a method and system for dispatching electric power services based on 5G communication hierarchical classification, relating to the field of 5G slicing technology. By utilizing prediction models and real-time monitoring data, this method effectively predicts network traffic and dynamically adjusts network resources based on different levels of electric power service needs, ensuring that high-priority electric power services can quickly obtain the necessary network support, thereby improving the overall network service quality and the operational efficiency of electric power services. Furthermore, through graph neural networks, network resource allocation is optimized, achieving accurate analysis and response to electric power service classification, enhancing network predictability and stability, and supporting more complex electric power service applications.

Description

Technical Field

[0001] The present invention relates to the field of 5G slicing technology, and in particular to a method and system for dispatching electric power services based on 5G communication hierarchical classification. Background Art

[0002] 5G network slicing technology is a core network architecture innovation that allows operators to create multiple virtual networks within the same physical network. Each virtual network can provide customized network attributes and resource allocation for specific services, applications, or users. This is achieved through software-defined networking (SDN) and network function virtualization (NFV), and can flexibly configure key parameters such as bandwidth, latency, reliability, and security. 5G network slicing supports a wide range of application scenarios, such as the Internet of Things (IoT), vehicle-to-everything (V2X), telemedicine, and smart manufacturing. By dynamically partitioning network resources, it can meet the specific network performance requirements of different applications.

[0003] Among them, the hierarchical classification method of power 5G services aims to optimize the data communication needs of the power industry through 5G network technology. The hierarchical classification can effectively allocate and optimize 5G network resources according to the business importance and urgency of data transmission within the power system, which helps to improve the operating efficiency and reliability of the power system, support applications such as smart grids, remote monitoring and automated management, and ensure high response speed and network stability for key operations.

[0004] Currently, existing technologies are unable to effectively prioritize different services, resulting in inaccurate resource allocation and an inability to prioritize network requirements for high-priority services such as emergency data communications and real-time monitoring. The lack of data analysis tools limits the accuracy of existing technologies in traffic forecasting and network adjustments, leading to insufficient network resources during periods of high demand, impacting the efficiency and reliability of power services. Failure to promptly adjust and provide sufficient network resources for high-priority services delays the processing of critical data, impacting the demand response and timeliness of power services.

[0005] Therefore, in addition to the lack of priority distinction, the existing technology also has the disadvantage that network resource allocation cannot respond to dynamic changes in network load in a timely manner. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the purpose of the present invention is to provide a power business scheduling method and system based on 5G communication hierarchical classification. By utilizing prediction models and real-time monitoring data, it can effectively predict network traffic and dynamically adjust network resources according to different levels of power business needs, ensuring that high-priority power businesses can quickly obtain the necessary network support, thereby improving the overall network service quality and the operating efficiency of power businesses. By optimizing network resource allocation through graph neural networks, it can achieve accurate analysis and response to power business classification, enhance the predictability and stability of the network, and support more complex power business applications.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0008] A first aspect of the present invention provides a method for dispatching electric power services based on 5G communication hierarchical classification, comprising the following steps:

[0009] Obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, prioritize it, and generate priority business classification status;

[0010] Use business prediction models to predict power-related network traffic, identify key traffic events that potentially impact power services based on priority business classification status and real-time network bandwidth data, and generate traffic impact prediction indicators;

[0011] Adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, optimize the response time of key power businesses based on current network load, and generate response efficiency improvement indicators;

[0012] A resource allocation model is used to implement dynamic resource allocation under network slicing management based on the response efficiency improvement index, adjust network resources according to the priority needs of the power business, generate resource configuration optimization information, and complete the power business scheduling task according to the resource configuration optimization information.

[0013] A second aspect of the present invention provides a power service dispatching system based on 5G communication hierarchical classification, including:

[0014] The network status monitoring module is configured to obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, prioritize it, and generate priority business classification status;

[0015] The traffic analysis and prediction module is configured to use the business prediction model to predict the power-related network traffic, identify key traffic events that may affect the power business based on the priority business classification status and real-time network bandwidth data, and generate traffic impact prediction indicators;

[0016] A routing optimization module is configured to adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, optimize the response time of key power businesses based on current network load, and generate response efficiency improvement indicators;

[0017] The resource configuration management module is configured to use the resource allocation model to implement dynamic resource allocation under network slicing management according to the response efficiency improvement index, adjust network resources according to the priority needs of the power business, generate resource configuration optimization information, and complete the power business scheduling task according to the resource configuration optimization information.

[0018] One or more of the above technical solutions have the following beneficial effects:

[0019] The present invention discloses a method and system for dispatching electric power services based on 5G communication hierarchical classification. By utilizing prediction models and real-time monitoring data, network traffic is effectively predicted and network resources are dynamically adjusted according to different levels of electric power service needs, ensuring that high-priority electric power services can quickly obtain necessary network support, thereby improving the overall network service quality and the operating efficiency of electric power services. By optimizing network resource allocation through graph neural networks, accurate analysis and response to electric power service classification are achieved, the predictability and stability of the network are enhanced, and more complex electric power service applications are supported.

[0020] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0022] Figure 1 This is a flow chart of a method for dispatching electric power services based on 5G communication hierarchical classification in Embodiment 1 of the present invention;

[0023] Figure 2 A flow chart showing the state of generating priority service classification in the first embodiment of the present invention;

[0024] Figure 3 This is a flow chart of generating a traffic impact prediction indicator in the first embodiment of the present invention;

[0025] Figure 4This is a flow chart of generating a response efficiency improvement indicator in Example 1 of the present invention;

[0026] Figure 5 A flow chart of generating resource configuration optimization information in embodiment 1 of the present invention;

[0027] Figure 6 This is a flow chart of generating adjustment feedback records in embodiment 1 of the present invention;

[0028] Figure 7 This is a flow chart of generating network efficiency evaluation results in embodiment 1 of the present invention;

[0029] Figure 8 This is a structural diagram of the power business dispatching system based on 5G communication hierarchical classification in Example 2 of the present invention. DETAILED DESCRIPTION

[0030] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations;

[0032] Example 1:

[0033] The first embodiment of the present invention provides a method for dispatching electric power services based on 5G communication hierarchical classification, such as Figure 1 As shown, the following steps are included:

[0034] S1: Obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, and prioritize it to generate priority business classification status.

[0035] S2: Use the business prediction model to predict power-related network traffic, identify key traffic events that potentially affect power services based on priority business classification status and real-time network bandwidth data, and generate traffic impact prediction indicators.

[0036] S3: Adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, optimize the response time of key power businesses based on the current network load, and generate response efficiency improvement indicators.

[0037] S4: Use the resource allocation model to implement dynamic resource allocation under network slicing management based on the response efficiency improvement index, adjust network resources according to the priority needs of the power business, generate resource configuration optimization information, and complete the power business scheduling task according to the resource configuration optimization information.

[0038] S5: Collect feedback information on network operation based on the power business dispatch situation, optimize and adjust related parameters, make judgment logic adjustments and match network changes, and generate adjustment feedback records.

[0039] S6: Perform network performance evaluation based on the adjustment feedback records, evaluate the operating efficiency and business responsiveness of the power 5G network, and generate network efficiency evaluation results.

[0040] In S1, the priority service classification status includes service urgency level, traffic priority, and network response indicators.

[0041] Real-time network bandwidth data includes network bandwidth utilization, latency, and packet loss rate.

[0042] like Figure 2 As shown in the figure, the steps for obtaining real-time data of power business traffic and network bandwidth, evaluating the network status based on business classification requirements, identifying and classifying power business traffic, and prioritizing it are as follows:

[0043] S101: Based on service classification requirements, monitor network bandwidth usage, latency, and packet loss rate, record network parameter changes in real time, analyze long-term parameter trends, and determine the network status to obtain a network health index.

[0044] In a specific implementation, based on service tiering requirements, multiple monitoring nodes are deployed at key locations across the network to collect real-time data on network bandwidth usage, latency, and packet loss. Data is continuously recorded and analyzed, using data smoothing techniques and trend analysis methods to ensure accurate tracking of network parameter changes and identification of long-term trends. A network health index is calculated based on the comprehensive indicators of the set network performance thresholds. This health index adjusts the impact of each indicator using weight coefficients, outputs the network's health status, and provides basic data for subsequent steps. The network performance thresholds include bandwidth utilization thresholds, latency thresholds, and packet loss thresholds, all of which are custom-set based on experience.

[0045] In this embodiment, the service classification requirements are divided into emergency level, high priority level, regular level and background level from high to low.

[0046] Emergency level (highest):

[0047] These services, including power system fault response and accident handling, require immediate response and place extremely high demands on network stability and response speed.

[0048] High priority (High):

[0049] These services include real-time power monitoring and status detection of high-load equipment. Although these services are not as critical as emergency-level services, they have high requirements for network performance.

[0050] Regular level (medium):

[0051] These services include daily data collection and equipment maintenance information transmission. These services have relatively low requirements for network latency and bandwidth.

[0052] Background level (low):

[0053] These services, including long-term data analysis and archive transmission, can tolerate higher latency and have minimal requirements for immediacy.

[0054] The present invention configures nodes, resource configuration and data processing strategies based on the above business requirements, and its rules are as follows:

[0055] Node location selection:

[0056] For emergency and high-priority services, detection nodes should be deployed at the network core layer to ensure rapid response to critical business needs.

[0057] Detection nodes for regular and background services can be deployed at the access layer or edge layer to optimize costs and network resource allocation.

[0058] Resource allocation:

[0059] Detection nodes for emergency and high-priority services should be equipped with high-performance processing and storage resources to support fast data processing and immediate feedback.

[0060] Nodes for regular and background services can be configured with standard resources to meet basic operating requirements.

[0061] Data processing policy:

[0062] Emergency and high-priority business nodes need to implement real-time data analysis and priority processing mechanisms.

[0063] Regular and background services can use batch and delayed processing strategies to optimize network and server loads.

[0064] In addition, in this embodiment, all levels of detection nodes should ensure high-reliability connections with the main server or data center, especially nodes that handle emergency and high-priority services, and network stability should be ensured through multi-path and redundant design.

[0065] S102: Identify the business traffic that needs to be prioritized based on the traffic and error rate data in the network health index, prioritize them according to business criticality and urgency, and obtain a priority decision table.

[0066] In a specific embodiment, using traffic and error rate data, according to the formula Calculate the priority of each business flow, where Represents the flow rate, represents the error rate, and are adjustment coefficients used to balance the impact of traffic and error rate on priority;

[0067] Considering that business traffic with large traffic or high error rate needs to be processed first, square the error rate to amplify the priority in the case of high error rate and adjust the coefficient and Set according to the importance of the business. For example, for critical business, the impact of errors is more important than traffic, so May be greater than For example, if a business flow F=200, the error rate , set the adjustment coefficient and , the priority is calculated as:

[0068] .

[0069] The results show that based on the given traffic and error rate, the priority of this service traffic is 200.25, and the value needs to be compared with other service traffic to determine the processing order.

[0070] S103: reallocate high-priority service resources according to the priority decision table, adjust the network load distribution process, and generate a priority service classification state.

[0071] In one specific implementation, network resources are dynamically reallocated based on the generated priority decision table, prioritizing high-priority traffic. This involves adjusting network routing policies and bandwidth allocation. This optimizes network load to reduce latency and packet loss for critical services. Regular network performance reviews and adjustments to service priorities ensure continuous optimization and improvement of network service quality.

[0072] In this embodiment, the network resource allocation process includes:

[0073] Continuously monitor traffic usage at each network node and link, including metrics such as bandwidth utilization, latency, and packet loss rate;

[0074] Evaluate network resource usage based on traffic monitoring data and identify resource bottlenecks and overload points;

[0075] Develop network load balancing and traffic management strategies, and adjust resource allocation based on business priorities and network health indicators;

[0076] Through routing algorithms and bandwidth allocation, traffic is evenly distributed to various links and nodes to avoid overloading any single point;

[0077] Dynamically adjust traffic routing and resource allocation based on real-time monitoring data and network status to adapt to changes in network conditions.

[0078] The process of optimizing network load distribution includes:

[0079] Implement routing protocols, such as OSPF or BGP, to adjust routing decisions in real time based on network conditions and optimize traffic distribution;

[0080] Deploy SDN and dynamically adjust network traffic through a centralized controller to respond to various business needs;

[0081] By virtualizing network functions, such as virtualized load balancers and firewalls, resources can be expanded and service policies can be adjusted more flexibly to adapt to changing network loads.

[0082] Set and optimize Quality of Service (QoS) parameters, such as priority queuing, bandwidth reservation, and traffic shaping, to ensure that high-priority services receive the necessary resources;

[0083] Use machine learning algorithms to predict and analyze network traffic behavior, identify potential traffic peaks and abnormal behavior in advance, and adjust load distribution strategies in a timely manner;

[0084] Design network redundant paths and implement failover mechanisms to ensure that critical services can quickly switch to backup paths when a link fails, minimizing service interruptions.

[0085] In S2, the service forecasting model is the ARIMA (Autoregressive Integrated Moving Average) model, a time series forecasting model. Traffic shock prediction indicators include peak traffic, potential events, and accuracy information.

[0086] like Figure 3 As shown in the figure, the business prediction model is used to predict power-related network traffic. Based on the priority business classification status and real-time network bandwidth data, key traffic events that potentially affect power business are identified. The specific steps for generating traffic impact prediction indicators are as follows:

[0087] S201: Based on the priority business classification status, the ARIMA model is used to monitor the network traffic in the key time period, and through real-time data comparison and analysis, the key traffic intervals that may affect the power business are marked to obtain the risk traffic marking area.

[0088] In one specific implementation, based on the determined priority service classification status, an ARIMA model is deployed to predict network traffic during critical time periods using historical traffic data and real-time monitoring data. Through model refinement, the model accurately identifies critical traffic intervals that impact power services. During this phase, all monitored data is analyzed in real time and compared with the model's predictions. Abnormal or potentially risky traffic intervals are marked, forming a risky traffic marker zone. This marker zone is used for subsequent analysis to identify traffic patterns that significantly impact business operations.

[0089] S202: Analyze the traffic trend of the target period according to the risk traffic marking area, estimate the traffic in the next few hours, and obtain traffic peak warning information.

[0090] In a specific embodiment, based on the risk traffic marking area data, a time series prediction model is applied Calculate the traffic in the next few hours, where represents the traffic volume during the forecast period, Represents the traffic volume of the previous period, Represents the flow rate change rate.

[0091] The time series forecasting model predicts future traffic changes by analyzing historical traffic data and using a growth model. Represents the traffic change rate, which is the average traffic growth rate here. For example, if the traffic in the past hour is , the average growth rate (i.e. 5%), the traffic forecast for the next hour is:

[0092] .

[0093] Referring to the current risk traffic markers and historical growth trends, it is expected that the traffic will reach 1050MB in the next hour, which will help to issue an early warning when the traffic reaches a peak, so that appropriate network management measures can be taken.

[0094] S203: Identify and mark key traffic events that cause service interruption based on traffic peak warning information, evaluate the potential threat of the events to network stability, and generate traffic impact prediction indicators.

[0095] In a specific implementation, based on the traffic peak warning information, key traffic events that lead to service interruptions are further identified, that is, a detailed assessment of key events that affect network stability is conducted, including the nature of the event, the scope of impact, and its potential threat to the power business. Based on the analysis, traffic impact prediction indicators are generated. The indicators will provide decision support for network operations, ensuring the continuity of power business and the overall stability of the network.

[0096] In S3, a load balancing algorithm is used to optimize the response time of key power services. Response efficiency improvement indicators include adjusted routing efficiency, bandwidth utilization, and transmission rate.

[0097] like Figure 4 As shown in the figure, the routing of power business data is adjusted according to the traffic impact prediction index, and the network bandwidth and data path are optimized. The response time of key power business is optimized according to the current network load. The specific steps to generate the response efficiency improvement index are as follows:

[0098] S301: Monitor current network bandwidth usage based on traffic impact prediction indicators, adjust routing rules based on traffic data trends, and match differentiated service loads to obtain a routing efficiency index. Matching differentiated service loads involves adjusting network routing and resource allocation based on the varying characteristics of service traffic to optimize overall network performance and responsiveness. This involves analyzing and matching the differences in all service loads.

[0099] In a specific implementation, based on traffic impact prediction indicators, the bandwidth occupancy in the network is continuously monitored, with particular attention paid to high-risk and high-traffic areas. Combined with real-time and historical traffic data trends, routing rules are adjusted to adapt to the needs of different business loads and optimize data transmission efficiency. In this process, the traffic carrying capacity and latency of each routing path are evaluated, and the effect of routing adjustment is quantified through a comprehensive routing efficiency index. The routing efficiency index is calculated by the performance improvement of each routing path and the balance of load distribution, ensuring efficient and stable transmission of all power business data.

[0100] The specific steps to adjust routing rules to meet the needs of different business loads include:

[0101] 1. Collect business traffic data:

[0102] Collect and analyze data on various types of business traffic, including traffic volume, transmission frequency, priority, and sensitivity to delay.

[0103] 2. Classify business load:

[0104] Based on the collected data, business traffic is classified into several categories, such as emergency business, high-priority business, regular business, and background business; the specific requirements and network performance of each type of business are identified, such as bandwidth requirements and tolerance for delay.

[0105] 3. Quantitative analysis of business needs:

[0106] Conduct quantitative analysis on each type of business traffic to determine its demand for network resources; analyze the behavior patterns of different business traffic in the network, such as peak traffic hours and traffic growth trends.

[0107] 4. Assess business impact:

[0108] Evaluate the impact of each service flow on network performance, especially when resources are limited or the network is congested.

[0109] 5. Optimize routing strategy:

[0110] Develop routing strategies based on the classification and characteristics of service loads, such as allocating high-bandwidth paths to high-priority services and allocating the shortest paths to delay-sensitive services.

[0111] 6. Adjust resource allocation:

[0112] Dynamically adjust the allocation of bandwidth and routing resources based on the importance of the business and network needs; balance the load to ensure the most reasonable utilization of network resources and avoid some businesses from excessively occupying resources and affecting other businesses.

[0113] 7. Deployment adjustment:

[0114] Implement the above matching strategy in the network and adjust the configuration of network devices, such as routing tables and bandwidth limits of routers and switches.

[0115] 8. Continuous monitoring and adjustment:

[0116] Monitor changes in business traffic and network performance, and continuously optimize matching strategies based on actual conditions; continuously adjust routing and resource allocation to adapt to changes in business and network conditions.

[0117] It should be noted that in the power 5G network, adjusting routing rules based on real-time and historical traffic data trends is a key process. First, by monitoring the traffic data of key nodes and links in real time and analyzing historical traffic data to determine the traffic patterns and trends in each time period, the data helps identify traffic peaks and valleys, as well as common data transmission problems. Next, time series analysis and prediction models are used to identify traffic patterns in key periods, and the corresponding network requirements are mapped according to the importance and urgency of different services. Based on these analysis results, routing strategies are designed and adjusted, such as selecting the path with the lowest latency for emergency services, while regular services can choose paths with lower costs or larger bandwidth. Load balancing algorithms are implemented to dynamically adjust traffic distribution to avoid overloading any single path. After the new strategy is deployed, its performance is continuously monitored, including overall network performance and the response time of key services, and adjustments are made based on real-time feedback to ensure optimal network performance. This method can ensure that the power 5G network can effectively adapt to current and future business needs and maintain efficient and stable network operation.

[0118] S302: Analyze the dynamic changes of network load during the critical period using the routing efficiency index, adjust the data transmission path according to the network capacity, implement load balancing and allocate network resources, and obtain a network response optimization table.

[0119] In a specific implementation, based on the obtained routing efficiency index, the dynamic changes in network load during critical periods are deeply analyzed. According to the current network capacity and the future traffic prediction results of the previous steps, the data transmission path is adjusted and a load balancing strategy is implemented. At this stage, network resources are dynamically allocated through an algorithm to optimize the processing response of each business traffic flow, and a network response optimization table is generated to record the results of each data path adjustment and resource allocation, which is used to evaluate and guide subsequent network management and optimization measures.

[0120] Based on the current network capacity and the future traffic prediction results from the previous step, adjust the data transmission path and implement the load balancing strategy as follows:

[0121] 1. Select a path based on business priority:

[0122] Emergency services, such as power outage response, should be prioritized for transmission over the path with the lowest latency and highest reliability.

[0123] High-priority services, such as real-time monitoring and control instructions, require a lower-latency path.

[0124] Business as usual: A path where slightly higher latency is acceptable and is typically the lower-cost option.

[0125] 2. Analyze the traffic density and remaining capacity of each link:

[0126] Link congestion prediction: Leverage historical and real-time traffic data to predict which links may experience congestion.

[0127] Capacity optimization: Prioritizes underutilized links to balance network load.

[0128] 3. Consider the latency and packet loss rate of the data path:

[0129] Select paths with low latency and low packet loss, especially for latency-sensitive services.

[0130] Evaluate path performance regularly and look for alternative paths if performance degradation is observed.

[0131] 4. Apply intelligent routing algorithms for dynamic path adjustment:

[0132] Dynamic routing: Routers such as Open Shortest Path First (OSPF) or Border Gateway Protocol (BGP) can dynamically adjust routes based on the current state of the network.

[0133] Software-defined networking (SDN) technology: Dynamically manages the paths of data flows through a central controller, allowing rapid adjustments in response to changes in network status.

[0134] 5. Implement load balancing strategy:

[0135] Weight-based load balancing: Assigns weights to different data paths and dynamically adjusts based on current traffic and performance indicators.

[0136] Redundant path utilization: Set up redundant paths for critical services to ensure rapid switchover when the primary path fails.

[0137] 6. Continuous monitoring: Monitor the performance indicators of all critical paths in real time.

[0138] 7. Adaptive Adjustment: Automatically adjust paths when performance degradation is detected or possible service impact is foreseen.

[0139] S303: Adjust the network configuration according to the network response optimization table, and use the load balancing algorithm to optimize the processing speed of the power business. Adjust the resource allocation ratio for key areas of business volume and generate response efficiency improvement indicators.

[0140] In a specific implementation, the load balancing algorithm formula is:

[0141] .

[0142] Calculate resource allocation efficiency and generate resource allocation ratio ,in, Represents the weight of the i-th service area, referring to the service priority and current load situation, Represents the current load of the i-th business area, reflecting the number of active businesses within the area. Represents the total available resources of the network and the total amount of resources that can be shared by all business areas. Represents the total number of business areas.

[0143] There are two business areas with weights of 2 and 1.5 respectively. The current loads are 300 and 500 respectively. The total resources are 1000. The resource allocation ratio of each business area is calculated as follows:

[0144] .

[0145] Calculate the resource allocation ratio for the first business area:

[0146] .

[0147] Calculate the resource allocation ratio for the second business area:

[0148] .

[0149] The calculation results show that the first business area and the second business area can be allocated approximately 444 and 556 resources respectively, indicating that resources are reasonably allocated according to the activity and priority of the business areas, ensuring the response efficiency of key areas.

[0150] In S4, a graph neural network is used to build a resource allocation model. Resource configuration optimization information includes dynamic resource allocation results, resource utilization optimization level, and slice management efficiency.

[0151] like Figure 5 As shown in the figure, the resource allocation model is used to implement dynamic resource allocation under network slicing management according to the response efficiency improvement index, adjust network resources according to the priority needs of power services, generate resource configuration optimization information, and complete the power service scheduling task according to the resource configuration optimization information. The specific steps are as follows:

[0152] S401: Use graph neural networks to continuously monitor the network usage of power services according to response efficiency improvement indicators, identify peak resource usage areas, adjust network resource configuration based on the identification results, optimize service response speed, and obtain an overview of network adjustments.

[0153] In a specific embodiment, by analyzing the node importance index output by the graph neural network, the formula Calculate the resource usage intensity R of each region, where represents the importance index of the i-th node, Represents the activity of the node, and n is the total number of nodes.

[0154] Graph neural networks analyze the usage of power business networks through their node links and weights, where each node represents a network device or service in a region, and the importance index of the node and activity This can be obtained through network traffic monitoring and historical data analysis. For example, if there are three nodes in a network, their importance index and activity are and , then the resource usage intensity is calculated as follows:

[0155] .

[0156] The results show that based on the data analyzed by the graph neural network, the resource usage intensity of the entire network is 380, indicating that the current network configuration needs to be optimized for peak areas to improve response efficiency.

[0157] S402: Perform detailed analysis of resource allocation based on the network adjustment overview to verify whether network requirements of high-priority services are met, and adjust and optimize the resource allocation process to obtain optimized resource configuration.

[0158] In a specific implementation, a detailed analysis of resource configuration is performed based on the network adjustment overview to check whether the existing network resource configuration meets the needs of high-priority services, especially under high-load conditions. If it is found that the resource configuration is insufficient or unbalanced, necessary adjustments and optimizations are made to ensure that all key services can operate normally. Through this method, not only the resource configuration is optimized, but also the efficiency and responsiveness of the entire network are improved, resulting in a more efficient optimized resource configuration result.

[0159] S403: Refine the management process of network slicing based on optimized resource configuration, adjust resource configuration according to actual business needs and network status, continuously optimize network performance, and generate resource configuration optimization information.

[0160] In a specific implementation, based on the optimized resource configuration, the management process of network slicing is refined and improved, and resource allocation is dynamically adjusted according to specific business needs and the current network status to adapt to the ever-changing business and network conditions, ensuring that network resource configuration can continue to meet the operational needs of the power business while improving the overall performance and stability of the network. Through this continuous optimization and adjustment, resource configuration optimization information is generated, which will provide important decision-making support for future network operations and management.

[0161] In S5, Figure 6As shown in the figure, according to the power business dispatch situation, feedback information of network operation is collected, related parameters are optimized and adjusted, judgment logic is adjusted to match network changes, and the steps of generating adjustment feedback records are as follows:

[0162] S501: Collect feedback information on network operation based on the power business dispatch situation, analyze the feedback information, monitor performance deviations or abnormal patterns, and adjust monitoring thresholds based on data fluctuations to obtain feedback analysis results.

[0163] In a specific implementation, the systematic collection and analysis of network operation feedback information includes monitoring of network performance deviations and abnormal patterns, as well as timely adjustment of relevant monitoring thresholds. By analyzing the collected data fluctuations and feedback, it is determined whether the existing monitoring thresholds need to be adjusted to better respond to changes in network status. The analysis results will form a feedback analysis result report, which records in detail the current operation status of the network and potential adjustment needs, providing a basis for subsequent parameter adjustments.

[0164] S502: Adjust parameters of the target network performance indicators according to the feedback analysis results, including bandwidth utilization and delay time, to match the current network load and service requirements, and obtain a parameter adjustment overview.

[0165] In a specific implementation, based on the feedback analysis results, detailed parameter adjustments are made to the target network performance indicators, including adjustments to key performance parameters such as network bandwidth utilization and latency, to better match the current network load and power business needs. The purpose is to optimize the configuration and use of network resources through real-time data to ensure the best match between network performance and business needs. The generated parameter adjustment profile will describe in detail the background, purpose and expected effect of each parameter adjustment.

[0166] S503: Analyze the adjusted network behavior using the parameter adjustment profile, compare network performance data before and after the adjustment, adjust the network configuration to match the network changes, and generate an adjustment feedback record.

[0167] In a specific implementation, a comprehensive analysis of the adjusted network behavior is performed. The analysis not only compares the network performance data before and after the adjustment, but also involves timely adjustments to the network configuration to match the network changes. This process ensures that all adjustment measures can effectively respond to the actual network operating conditions, and then generates an adjustment feedback record. The record will reflect in detail the effect of the network adjustment and any areas that need further adjustment, providing important information for continuously improving network performance and responsiveness.

[0168] In S6, the network efficiency evaluation results include efficiency indicators, responsiveness level, and resource allocation success rate.

[0169] like Figure 7As shown, the network performance evaluation is performed based on the adjustment feedback records to evaluate the operation efficiency and service responsiveness of the power 5G network. The specific steps for generating the network efficiency evaluation results are as follows:

[0170] S601: Monitor network performance in real time based on the adjustment feedback record, collect key performance data, identify performance bottlenecks, and obtain preliminary performance evaluation information.

[0171] In a specific implementation, real-time network performance monitoring is implemented to systematically collect and analyze key performance data, including core indicators such as response time and connection stability. During this process, special attention is paid to the identification of performance bottlenecks. Through monitoring data and real-time feedback, key problem areas affecting network efficiency are quickly located. The purpose is to form a comprehensive preliminary performance evaluation information, which records in detail the current performance status of the network and potential improvement areas.

[0172] S602: Evaluate the responsiveness and operating efficiency of the electric power 5G network according to the preliminary performance evaluation information, conduct comparative analysis based on historical performance data, and optimize network performance based on the analysis results to obtain a performance comparison record.

[0173] In a specific embodiment, the application performance comparison index is calculated by the formula Calculate the performance improvement percentage , where Represents the performance indicators in the current evaluation cycle, Represents the performance indicators within the same historical period.

[0174] This formula is used to compare the current performance of the power 5G network with the past performance, expressing the growth or decline as a percentage. For example, if the performance indicator of the current cycle is 120, the historical performance index for the same period If is 100, the performance improvement percentage is calculated as follows:

[0175] .

[0176] The results show that the performance of the current power 5G network has improved by 20% compared with historical performance, reflecting that the optimization measures taken have effectively improved responsiveness and operational efficiency.

[0177] S603: Use the performance comparison records to re-evaluate the performance of the power 5G network, adjust the configuration based on business needs and network resource distribution, determine the optimal configuration of network resources, and generate network efficiency evaluation results.

[0178] In a specific implementation, the performance comparison records are used to re-evaluate the performance of the power 5G network. According to the current business needs and the actual distribution of network resources, the network configuration is refined and adjusted to ensure that the network resource configuration can meet the needs of business operations to the greatest extent possible. Through this dynamic resource configuration and continuous performance evaluation, the optimal configuration of network resources is judged and determined. The generated network efficiency evaluation results will comprehensively reflect the overall operating efficiency and business responsiveness of the power 5G network, providing a scientific basis for future network management and optimization.

[0179] The purpose of re-evaluating the performance of the power 5G network is to analyze the latest performance evaluation results, especially the deviation from the set performance targets (such as maximum latency, minimum bandwidth guarantee, and service quality level). If the performance fails to meet the predetermined targets or there is obvious performance degradation, it will become a direct basis for adjusting the configuration.

[0180] As business develops and technology advances, new demands may arise, such as new service types or an increase in the number of users. These changes may require more resources or more complex configurations to support the new business demands.

[0181] Based on the latest network monitoring data, analyze the resource utilization of each node and link. If it is found that resources are unevenly distributed or some resources are overloaded, it is also necessary to adjust the configuration to optimize resource usage.

[0182] Identification of any network failures or security vulnerabilities caused by improper configuration is also an important basis for adjustment. Ensuring network reliability and security is the core goal of continuous configuration adjustment.

[0183] Specifically, based on current business needs and the actual distribution of network resources, the specific steps for refining and adjusting network configuration are as follows:

[0184] 1. Detailed analysis of performance evaluation report:

[0185] Review the re-evaluation performance report in detail, especially the comparison between the actual performance of each performance indicator and the expected target.

[0186] 2. Identify areas for improvement:

[0187] Based on performance reports, identify areas for improvement such as network bottlenecks, latency issues, insufficient bandwidth, etc.

[0188] Develop an adjustment plan:

[0189] Develop specific adjustment plans based on identified issues and changes in business needs, including adding routers, replacing or upgrading hardware, adjusting routing protocol settings, optimizing load balancing strategies, etc.

[0190] Implement the configuration changes:

[0191] Implement configuration changes during planned maintenance windows, including updating hardware settings, software configurations, and network topology.

[0192] 3. Monitor the effect of changes:

[0193] After changes are implemented, monitor the network's performance response and behavior to ensure that all adjustments have the desired effect.

[0194] 4. Continuous optimization:

[0195] Treat this process as a continuous cycle, conduct performance evaluations regularly, and continuously optimize network configurations based on the evaluation results to ensure optimal performance and stable operation of the network.

[0196] Example 2:

[0197] The second embodiment of the present invention provides a power business dispatching system based on 5G communication classification, such as Figure 8 As shown, including:

[0198] The network status monitoring module is configured to obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, prioritize it, and generate priority business classification status;

[0199] The traffic analysis and prediction module is configured to use the business prediction model to predict the power-related network traffic, identify key traffic events that may affect the power business based on the priority business classification status and real-time network bandwidth data, and generate traffic impact prediction indicators;

[0200] A routing optimization module is configured to adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, optimize the response time of key power businesses based on current network load, and generate response efficiency improvement indicators;

[0201] The resource configuration management module is configured to use the resource allocation model to implement dynamic resource allocation under network slicing management according to the response efficiency improvement index, adjust network resources according to the priority needs of the power business, generate resource configuration optimization information, and complete the power business scheduling task according to the resource configuration optimization information.

[0202] The performance evaluation and feedback module is configured to collect network operation feedback information based on power service dispatch, optimize and adjust associated parameters, adjust judgment logic to match network changes, and generate adjustment feedback records. Based on the adjustment feedback records, network performance evaluation is performed to assess the operational efficiency and service responsiveness of the power 5G network, generating network efficiency evaluation results.

[0203] The steps involved in the above embodiment 2 correspond to those in the method embodiment 1. For the specific implementation method, please refer to the relevant description part of the embodiment 1.

[0204] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

[0205] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage) containing computer-usable program code.

[0206] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for dispatching electric power services based on 5G communication hierarchical classification, characterized in that: The following steps are involved: Obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, prioritize it, and generate priority business classification status; Using traffic and error rate data, according to the formula P = αF + βE 2 Calculate the priority of each service flow. Where F represents the flow rate, E represents the error rate, and α and β are adjustment coefficients used to balance the impact of flow rate and error rate on priority, respectively. The business prediction model is used to predict power-related network traffic. Based on the priority business classification status and real-time network bandwidth data, key traffic events that potentially affect power business are identified, and traffic impact prediction indicators are generated. Specifically, Based on the priority business classification status, the ARIMA model is used to monitor network traffic in key time periods. Through real-time data comparison and analysis, key traffic intervals that potentially affect power business are marked to obtain risk traffic marking areas. Analyze traffic trends during target periods according to risky traffic marking areas, estimate traffic within the next few hours, and obtain traffic peak warning information; Identify and mark key traffic events that cause service interruptions based on traffic peak warning information, assess the potential threat of these events to network stability, and generate traffic impact prediction indicators. Adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, optimize the response time of key power businesses based on current network load, and generate response efficiency improvement indicators; The resource allocation model is used to implement dynamic resource allocation under network slicing management based on the response efficiency improvement index. Network resources are adjusted according to the priority needs of the power business, resource configuration optimization information is generated, and the power business scheduling task is completed according to the resource configuration optimization information. Specifically: Using graph neural networks to continuously monitor network usage for power services based on response efficiency improvement indicators, we identify peak resource usage areas, adjust network resource allocation based on the identified results, optimize service response speed, and obtain an overview of network adjustments. Conduct detailed resource allocation analysis based on the network adjustment overview to verify whether network requirements for high-priority services are met, and adjust and optimize the resource allocation process to achieve optimal resource configuration. Refine the management process of network slicing based on optimized resource allocation, then adjust resource allocation according to actual business needs and network status, continuously optimize network performance, and generate resource configuration optimization information.

2. The power service scheduling method based on 5G communication hierarchical classification according to claim 1, characterized in that: The priority service classification status includes service urgency level, traffic priority and network response index.

3. The power service dispatching method based on 5G communication hierarchical classification according to claim 1, characterized in that: The traffic impact prediction indicators include peak traffic, potential events and accuracy information.

4. The power service scheduling method based on 5G communication hierarchical classification according to claim 1, characterized in that: The response efficiency improvement index includes adjusted routing efficiency, bandwidth utilization and transmission rate.

5. The power service scheduling method based on 5G communication hierarchical classification according to claim 1, characterized in that: The resource configuration optimization information includes dynamic resource allocation results, resource utilization optimization degree, and slice management efficiency.

6. The power service dispatching method based on 5G communication hierarchical classification according to claim 1, characterized in that: Obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, and prioritize it. The specific steps for generating priority business classification status are as follows: Based on business classification requirements, it monitors network bandwidth usage, latency, and packet loss, records network parameter changes in real time, analyzes long-term parameter trends, and determines network status to obtain a network health index. Identify the business traffic that needs to be prioritized based on the traffic and error rate data in the network health index, sort the priorities by business criticality and urgency, and obtain a priority decision table; Redistribute high-priority service resources according to the priority decision table, adjust the network load distribution process, and generate a priority service classification state.

7. The power service dispatching method based on 5G communication hierarchical classification according to claim 1, characterized in that: Adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, and optimize the response time of key power business based on the current network load. The specific steps to generate response efficiency improvement indicators are as follows: Monitor current network bandwidth usage based on traffic impact prediction indicators, adjust routing rules based on traffic data trends, and match different business loads to obtain a routing efficiency index. The routing efficiency index is used to analyze the dynamic changes of network load during critical periods, adjust the data transmission path according to network capacity, implement load balancing and allocate network resources, and obtain a network response optimization table; Adjust the network configuration according to the network response optimization table, and use the load balancing algorithm to optimize the processing speed of power business. Adjust the resource allocation ratio for key areas of business volume and generate response efficiency improvement indicators.

8. The power service dispatching method based on 5G communication hierarchical classification according to claim 1, characterized in that: It also includes the feedback process for power business dispatch tasks, and the specific steps include: Collect feedback information on network operation based on power business dispatch, optimize and adjust related parameters, make judgment logic adjustments to match network changes, and generate adjustment feedback records; Perform network performance evaluation based on the adjustment feedback records, evaluate the operating efficiency and business responsiveness of the power 5G network, and generate network efficiency evaluation results.

9. The power service dispatching method based on 5G communication hierarchical classification according to claim 8, characterized in that: The network efficiency evaluation results include efficiency indicators, responsiveness levels, and resource allocation success rates.

10. The power service dispatching method based on 5G communication hierarchical classification according to claim 8, characterized in that: Collect feedback information on network operation based on power business dispatch, optimize and adjust related parameters, make judgment logic adjustments to match network changes, and generate adjustment feedback records in the following specific steps: Collect feedback information on network operation based on power business dispatch, analyze the feedback information, monitor performance deviations or abnormal patterns, and adjust monitoring thresholds based on data fluctuations to obtain feedback analysis results; Adjust parameters based on the target network performance indicators, including bandwidth utilization and latency, according to the feedback analysis results to match the current network load and business needs, and obtain a parameter adjustment overview; Use the parameter adjustment profile to analyze the adjusted network behavior, compare the network performance data before and after the adjustment, adjust the network configuration to match the network changes, and generate adjustment feedback records.

11. The power service dispatching method based on 5G communication hierarchical classification according to claim 8, characterized in that: Perform a network performance evaluation based on the adjustment feedback records to assess the operational efficiency and service responsiveness of the power 5G network. The specific steps for generating the network efficiency evaluation results are as follows: Monitor network performance in real time based on adjustment feedback records, collect key performance data, identify performance bottlenecks, and obtain preliminary performance evaluation information; Evaluate the responsiveness and operational efficiency of the power 5G network based on preliminary performance evaluation information, conduct comparative analysis based on historical performance data, and optimize network performance based on the analysis results to obtain performance comparison records; Use performance comparison records to re-evaluate the performance of the power 5G network, adjust the configuration based on business needs and network resource distribution, determine the optimal configuration of network resources, and generate network efficiency evaluation results.

12. A power business dispatching system based on 5G communication hierarchical classification, characterized in that: The power service scheduling method based on 5G communication hierarchical classification according to any one of claims 1 to 11 is adopted, comprising: The network status monitoring module is configured to obtain real-time data on power business traffic and network bandwidth, conduct network status assessment based on business classification requirements, identify and classify power business traffic, prioritize it, and generate priority business classification status; The traffic analysis and prediction module is configured to use the business prediction model to predict the power-related network traffic, identify key traffic events that may affect the power business based on the priority business classification status and real-time network bandwidth data, and generate traffic impact prediction indicators; A routing optimization module is configured to adjust the routing of power business data based on traffic impact prediction indicators, optimize network bandwidth and data paths, optimize the response time of key power businesses based on current network load, and generate response efficiency improvement indicators; The resource configuration management module is configured to use the resource allocation model to implement dynamic resource allocation under network slicing management according to the response efficiency improvement index, adjust network resources according to the priority needs of the power business, generate resource configuration optimization information, and complete the power business scheduling task according to the resource configuration optimization information.

13. The power service dispatching system based on 5G communication hierarchical classification according to claim 12, characterized in that: It also includes a performance evaluation feedback module, which is configured to collect feedback information on network operation based on the power business scheduling situation, optimize and adjust related parameters, make judgment logic adjustments and match network changes, generate adjustment feedback records, perform network performance evaluation based on the adjustment feedback records, evaluate the operating efficiency and business response capabilities of the power 5G network, and generate network efficiency evaluation results.

Images