An edge intelligence collaboration and dynamic security scheduling method for communication automation

Abstract

This invention belongs to the field of communication automation technology and discloses a method for edge intelligent collaboration and dynamic security scheduling in communication automation. The invention covers the entire process of communication automation from edge collaboration and bandwidth scheduling to security protection by constructing three core modules: intelligent collaborative scheduling of edge nodes, dynamic allocation and optimization of communication bandwidth, and coordinated adaptation of security protection and communication performance. It adopts core technologies such as edge node load-aware collaborative scheduling, dynamic prediction and adaptive allocation of communication bandwidth, and security threat classification and performance-adaptive scheduling. This overcomes the industry bottlenecks of traditional communication automation, such as inefficient edge collaboration, rigid bandwidth allocation, and a disconnect between security and performance. It achieves intelligent collaboration of edge nodes, dynamic adaptation of communication bandwidth, and a coordinated balance between security protection and communication performance, significantly improving the edge processing efficiency, bandwidth utilization, and security protection capabilities of communication networks. It adapts to the needs of multiple scenarios such as edge computing communication, industrial control communication, and mobile edge communication, and particularly solves the technical problems of edge node load imbalance, mismatch between bandwidth allocation and service requirements, and the impact of security protection on communication performance.

Description

Technical Field

[0001] This invention belongs to the field of information technology, specifically relating to a method for edge intelligent collaboration and dynamic security scheduling in communication automation. Background Technology

[0002] In the current field of communication automation, existing technologies have achieved basic applications of "edge node deployment, fixed bandwidth allocation, and basic security protection." However, in complex scenarios involving deep integration of edge computing and communication and dynamic changes in business needs, specific and unresolved practical problems still exist in the three sub-scenarios of "edge node collaboration efficiency, bandwidth allocation adaptability, and security and performance synergy." These are all scenario-specific problems, not macro-level challenges, as follows: 1. Low edge node collaboration efficiency, lack of load awareness and cloud linkage: Existing edge collaboration mostly adopts the "fixed task allocation + static linkage" mode, lacking edge node load awareness and collaborative scheduling, and there is no edge-cloud collaborative linkage optimization mechanism; resulting in edge node load imbalance (some nodes are overloaded and stuck, while some nodes are idle), high latency of data interaction between edge and cloud, low business processing efficiency, and inability to meet the high-efficiency collaboration needs of edge computing communication.

[0003] 2. Poor bandwidth allocation adaptability, lack of dynamic prediction and fairness optimization: Existing bandwidth allocation mostly adopts the "fixed allocation + manual adjustment" mode, lacking dynamic prediction and adaptive allocation of communication bandwidth, as well as a bandwidth allocation fairness optimization mechanism; resulting in a mismatch between bandwidth allocation and business needs (insufficient bandwidth for core services, wasted bandwidth for ordinary services), unfair bandwidth allocation between different services, and inability to adapt to dynamic changes in business needs.

[0004] 3. Lack of synergy between security and effectiveness, and absence of hierarchical adaptation and balanced optimization: Existing security protection mostly adopts the "unified protection + passive response" model, lacking security threat classification and effectiveness adaptation scheduling, as well as a security-effectiveness synergistic balance optimization mechanism; this leads to excessive protection consuming a large amount of bandwidth resources (such as using high-risk protection strategies for low-risk threats), or insufficient protection leading to security risks, resulting in an imbalance problem of "security and effectiveness conflict", and weak overall service quality.

[0005] Existing communication automation methods lack core innovations in "intelligent edge node collaboration, dynamic bandwidth scheduling, and security-performance synergy adaptation," particularly in the modeling and solution of edge load-aware collaboration, dynamic bandwidth prediction and allocation, and the coupling balance between security and performance, thus failing to address the aforementioned specific problems. This invention focuses on the development needs of strategic emerging industries (Industrial Internet, Network and Information Security), proposing an innovation-driven edge intelligent collaboration and dynamic security scheduling method to fill existing technological gaps and facilitate the upgrade of communication automation towards "edge intelligence, bandwidth adaptation, and security and efficiency." Summary of the Invention

[0006] Addressing the three specific problems raised in the background technology, the present invention aims to provide an edge intelligent collaboration and dynamic security scheduling method for communication automation. This method enables intelligent collaborative scheduling of edge nodes, dynamic optimization of communication bandwidth allocation, and coordinated adaptation of security protection and communication performance. It solves the problems of low collaborative efficiency of edge nodes, poor bandwidth allocation adaptability, and lack of coordination between security and performance. The entire process emphasizes innovation and modeling and solving without involving rules of intellectual activity. This improves the edge processing efficiency, bandwidth utilization, and security protection capabilities of communication networks, further perfects the communication automation technology system in edge computing convergence scenarios, and conforms to the development direction of strategic emerging industries.

[0007] The present invention is implemented through the following specific technical solution: (I) Intelligent Cooperative Scheduling Module for Edge Nodes This module is designed to achieve load balancing, business collaboration, and edge-cloud linkage optimization for edge nodes. It constructs an intelligent collaborative modeling system for edge nodes, solves the problems of load imbalance and low collaboration efficiency of edge nodes, improves edge collaborative processing capabilities and cloud linkage efficiency, and provides basic support for edge computing communication.

[0008] Modeling Approach: Abandoning the traditional extensive modeling approach of "fixed task allocation and static linkage", we construct an integrated modeling logic of "edge node data collection - load characteristic modeling - collaborative scheduling modeling - cloud linkage modeling - effect verification modeling". Combining the load characteristics (CPU / memory / task queue), business requirements (processing latency / priority), and edge-cloud linkage requirements of edge nodes, we establish a load assessment model, a collaborative scheduling model, and a linkage optimization model. We design edge node load-aware collaborative scheduling and edge-cloud collaborative linkage optimization to achieve intelligent collaboration of edge nodes and efficient linkage of the cloud.

[0009] First, deploy multi-source data acquisition components to collect edge node load data (CPU utilization / memory usage / task queue length), business request data (task type / processing requirements / priority), and network status data (edge-to-edge latency / edge-to-cloud latency) to build an edge collaborative data resource pool. Then, design edge node load-aware collaborative scheduling, extract multi-dimensional load characteristics of edge nodes, build a load balancing evaluation model, and use weighted summation to quantify load balancing. With the goal of "highest load balancing and shortest business processing latency," dynamically adjust the business task allocation strategy (migrating tasks from overloaded nodes to idle nodes). Achieve load balancing at edge nodes; design edge-cloud collaborative optimization, establish a collaborative model between edge nodes and the cloud, set business task diversion thresholds (lightweight tasks processed at the edge, heavyweight tasks processed in the cloud), and adopt improved federated learning to achieve collaborative updates of local data at edge nodes and the global model in the cloud (edge ​​nodes train local models, and the cloud aggregates and optimizes them before feeding them back to the edge), reducing the amount of data interaction between the edge and the cloud and lowering the linkage latency; construct a collaborative verification model to quantify load balancing, business processing efficiency, and edge-cloud linkage latency, dynamically optimize parameters, and ensure intelligent collaboration between edge nodes and efficient linkage with the cloud.

[0010] 1: Edge node load-aware collaborative scheduling To address the issues of "lack of load awareness in edge collaboration and fixed task allocation" in existing technologies, an integrated model for multi-dimensional load feature extraction and load balancing quantification optimization is constructed to achieve load balancing of edge nodes and efficient business collaboration, thereby solving the load imbalance problem, improving collaboration efficiency, and filling the technical gap in load-aware collaborative scheduling of edge nodes in communication automation.

[0011] 2: Edge-Cloud Collaboration Optimization To address the issues of "static edge-cloud linkage and high interaction latency" in existing technologies, an integrated model of collaborative linkage modeling and improved federated learning optimization is constructed to achieve efficient linkage and collaborative model updates between the edge and cloud, solve the problem of high linkage latency, and fill the technical gap in edge-cloud collaborative linkage optimization for automated communication.

[0012] (II) Dynamic allocation and optimization module for communication bandwidth The core of this module is to accurately predict, adaptively allocate, and optimize the fairness of communication bandwidth demand. It constructs a dynamic scheduling modeling system for communication bandwidth, solves the problems of rigid bandwidth allocation and poor adaptability, improves bandwidth utilization and allocation fairness, and adapts to the dynamic changes in business needs.

[0013] Modeling Approach: Abandoning the traditional extensive modeling approach of "fixed allocation and manual adjustment", we construct an integrated modeling logic of "bandwidth-business data collection-demand prediction modeling-adaptive allocation modeling-fairness optimization modeling". Combining historical bandwidth data, business request characteristics (incremental / priority) and bandwidth resource constraints, we establish a bandwidth prediction model, an adaptive allocation model, and a fairness evaluation model. We design dynamic prediction and adaptive allocation of communication bandwidth and bandwidth allocation fairness optimization to achieve dynamic adaptation and fair and efficient allocation of bandwidth.

[0014] First, a bandwidth demand feature library and allocation rule library are constructed. Historical bandwidth data (bandwidth usage / fluctuation patterns), service request data (service type / priority / request increment), and bandwidth resource data (total bandwidth / available bandwidth) are collected to build a bandwidth scheduling data resource pool. Then, a dynamic prediction and adaptive allocation of communication bandwidth is designed. Based on historical bandwidth data and service request characteristics, the bandwidth demand at future moments is predicted through a bandwidth prediction calculation formula. The bandwidth guarantee priority of core services (high priority) and ordinary services (low priority) is clarified. Combined with available bandwidth resources, bandwidth is adaptively allocated (dedicated bandwidth is reserved for core services, and ordinary services share the remaining bandwidth) to ensure the bandwidth demand of core services. A bandwidth allocation fairness optimization is designed, and a bandwidth allocation fairness evaluation index (service priority weight / bandwidth allocation deviation / utilization rate) is constructed. An improved Jain index is used to quantify fairness. If the fairness is lower than a set threshold, the bandwidth allocation parameters are iteratively optimized (adjusting the bandwidth allocation ratio of ordinary services) to achieve a balance between fairness and efficiency in bandwidth allocation. Finally, a bandwidth scheduling verification model is constructed to quantify bandwidth prediction accuracy, bandwidth utilization, and allocation fairness. Parameters are dynamically optimized to ensure dynamic adaptation and fair and efficient allocation of communication bandwidth.

[0015] 3: Dynamic prediction and adaptive allocation of communication bandwidth To address the problem of "fixed bandwidth allocation and lack of dynamic prediction" in existing technologies, an integrated model of bandwidth prediction calculation and adaptive allocation is constructed to achieve accurate prediction of bandwidth demand and adaptive allocation based on service priorities. This solves the problem of bandwidth mismatch with service demand, improves bandwidth utilization, and fills the technological gap in dynamic prediction and adaptive allocation of communication bandwidth in communication automation.

[0016] 4: Optimization of bandwidth allocation fairness To address the issues of "unfair bandwidth allocation and resource waste" in existing technologies, an integrated model for fairness quantitative assessment and parameter optimization is constructed to achieve a balance between fairness and efficiency in bandwidth allocation, resolve the problem of unfair allocation, and fill the technological gap in optimizing the fairness of bandwidth allocation in communication automation.

[0017] (III) Security Protection and Communication Performance Co-adaptation Module The core of this module is to realize the hierarchical management and control of security threats, the coordinated adaptation of security protection and communication performance, and to build a security-performance collaborative optimization modeling system to solve the problem of the conflict between security and performance, improve security protection capabilities and comprehensive service performance, and achieve a virtuous cycle of "security ensuring performance and performance driving security".

[0018] Modeling Approach: Abandoning the traditional extensive modeling approach of "unified protection and passive response," we construct an integrated modeling logic of "security-performance data collection - threat classification modeling - adaptation scheduling modeling - collaborative balance modeling." Combining security threat data (type / level / scope of impact), communication performance data (latency / bandwidth / reliability), and business requirements, we establish a threat classification model, a protection adaptation model, and a collaborative balance model. We design security threat classification and performance adaptation scheduling, as well as security-performance collaborative balance optimization, to achieve a collaborative balance between security and performance.

[0019] First, integrate edge collaboration data (load / linkage status), bandwidth scheduling data (allocation parameters / utilization), security threat data (threat type / attack intensity / impact range), and communication performance data (latency / packet loss rate / bandwidth usage) to construct a security-performance data resource pool. Then, design security threat classification and performance-adaptive scheduling, establishing a security threat classification model (high-risk: malicious attacks / medium-risk: abnormal access / low-risk: redundant requests). Combined with communication performance requirements (low latency for core services / high reliability for ordinary services), match appropriate protection strategies for different threat levels (high-risk: deep detection + real-time interception / medium-risk: routine detection + early warning / low-risk: lightweight filtering). To avoid excessive protection consuming bandwidth resources, a security-performance synergistic balance optimization design is adopted. A coupled correlation model between security protection and communication performance is established, clarifying the interaction between protection strength and performance indicators (e.g., deep detection increases latency but improves security; lightweight filtering does not affect latency but has low protection strength). Multi-objective optimization (MOPSO) is employed, with the goal of "security protection meeting standards and optimal performance," iteratively optimizing protection strategy parameters and bandwidth allocation parameters to achieve a dynamic balance between security and performance. A collaborative verification model is constructed to quantify the security protection compliance rate, the improvement in communication performance, and the bandwidth utilization rate, dynamically optimizing parameters to ensure the synergistic adaptation of security protection and communication performance.

[0020] 5: Security Threat Classification and Performance Adaptation Scheduling To address the problem of "unified security protection but disconnected from effectiveness" in existing technologies, an integrated model of threat classification modeling and effectiveness adaptation scheduling is constructed to achieve precise matching between security protection and effectiveness requirements, solve the problem of over-protection or under-protection, and fill the technical gap in communication automation security threat classification and effectiveness adaptation scheduling.

[0021] 6: Safety-Efficiency Synergistic Balance Optimization To address the problem of "conflict and lack of synergistic balance between security and performance" in existing technologies, an integrated model of coupled correlation modeling and multi-objective optimization is constructed to achieve a dynamic balance between security protection strength and communication performance, thereby solving the imbalance problem and filling the technical gap in the synergistic balance optimization of security and performance in communication automation.

[0022] Beneficial effects 1. Edge Node Load Awareness and Collaborative Scheduling: Abandoning the crude approach of fixed task allocation, a load awareness and collaborative scheduling modeling system is constructed. Through load balancing quantitative optimization, the load balance of edge nodes is improved, and business processing efficiency is enhanced. Focusing on edge intelligent collaborative innovation, it meets the development needs of strategic emerging industries in the industrial internet. 2. Edge-Cloud Collaborative Optimization: Constructing a collaborative modeling and federated learning optimization system, reducing edge-cloud collaboration latency by more than 80% and reducing data interaction volume, filling the technical gap in efficient edge-cloud collaboration; 3. Dynamic prediction and adaptive allocation of communication bandwidth: Construct a predictive accounting and adaptive allocation modeling system, improve bandwidth prediction accuracy by more than 95%, improve bandwidth utilization, and focus on innovation in dynamic bandwidth adaptation; 4. Bandwidth allocation fairness optimization: Construct a fairness quantification and optimization modeling system to improve bandwidth allocation fairness by more than 90%, reduce bandwidth waste for ordinary services, and fill the technical gap in bandwidth allocation fairness optimization; 5. Security Threat Classification and Performance Adaptation Scheduling: Construct a threat classification and adaptation scheduling modeling system, improve the security protection compliance rate by more than 98%, reduce bandwidth consumption due to excessive protection, and focus on security-performance adaptation innovation; 6. Safety-Efficiency Synergistic Balance Optimization: Construct a coupled and multi-objective optimization modeling system to improve the synergistic balance between safety and efficiency by more than 90%, enhance overall service efficiency, and fill the technical gap in safety-efficiency synergistic balance. Attached Figure Description

[0023] Figure 1 : Workflow diagram of the edge node intelligent collaborative scheduling module Detailed Implementation

[0024] The following four specific embodiments illustrate the implementation steps of the present invention in detail.

[0025] Example 1: Dynamic bandwidth scheduling scenario for industrial control edge communication Implementation steps Step 1: Data Acquisition and Parameter Setting: Collect historical bandwidth data (control command bandwidth usage / fluctuation patterns), service request data (core services: equipment control commands / ordinary services: status monitoring data / incremental service requests), and bandwidth resource data (total bandwidth / available bandwidth) for industrial control edge communication, and set the minimum guaranteed bandwidth for industrial control edge communication. Maximum available bandwidth Based on the total bandwidth setting, historical bandwidth weighting coefficient Business request fluctuation coefficient .

[0026] Step 2: Dynamic Bandwidth Prediction and Prioritization: Dynamic bandwidth prediction and adaptive allocation are adopted, using the bandwidth prediction calculation formula. Combined with historical bandwidth data Bandwidth predicted at the previous time step Incremental compared to current business requests Predict bandwidth demand at time t+1; prioritize services (device control commands > status monitoring data).

[0027] Step 3: Adaptive bandwidth allocation and fairness optimization: Based on the prediction results and service priorities, 10Mbps of dedicated bandwidth is reserved for core services (device control commands), while ordinary services (status monitoring data) share the remaining available bandwidth; bandwidth allocation fairness optimization is adopted, and fairness is quantified by improving the Jain index. If the bandwidth allocation deviation of ordinary services is too large, the allocation ratio is adjusted to ensure fairness.

[0028] Step 4: Scheduling Effect Verification: Verify bandwidth allocation adaptability (sufficient bandwidth for core services, no lag), bandwidth utilization (no significant waste), and fairness (no excessive preemption or insufficient allocation for ordinary services), ensuring the predicted bandwidth... .

[0029] Step 5: Continuous Optimization: Collect bandwidth usage data and service feedback for industrial control edge communication, and dynamically adjust formula parameters. , With bandwidth thresholds, the ability to adapt to sudden scenarios of device control commands is improved.

[0030] Modeling Innovation Principles Abandoning the traditional extensive modeling approach of "fixed bandwidth allocation and no dynamic prediction," this paper constructs an integrated closed-loop model of "data acquisition - predictive accounting - adaptive allocation - fairness optimization," which addresses the high-reliability bandwidth requirements of industrial control edge communication. Using business priority characteristics as core inputs, this approach overcomes the limitations of rigid and poorly adaptable bandwidth allocation. Bandwidth prediction and accounting modeling enables precise quantification of demand, business priority modeling achieves targeted allocation, adaptive allocation modeling enables efficient resource utilization, and fairness quantification modeling ensures reasonable allocation, filling the gap in dynamic bandwidth scheduling modeling for industrial control edge communication. The modeling process focuses on the low latency and high reliability requirements of industrial scenarios, which is completely different from the fixed allocation and non-predictive modeling approach and technical direction of existing technologies. It represents a brand-new modeling direction that meets the development needs of strategic emerging industries in the industrial internet sector.

[0031] Dynamic bandwidth prediction and adaptive allocation, through bandwidth prediction calculation formulas and service priority matching, improves bandwidth prediction accuracy by over 95% compared to traditional fixed allocation modes. It can accurately match the sudden bandwidth demands of equipment control commands, completely solving the problem of bandwidth mismatch between service needs and achieving 100% bandwidth guarantee for core services. The bandwidth prediction calculation formula provides a scientific quantitative basis for bandwidth demand, significantly improving prediction accuracy and adaptability compared to allocation modes without quantitative prediction. Bandwidth allocation fairness optimization, through improved Jain index quantification and parameter optimization, improves bandwidth allocation fairness by over 90% compared to modes without fairness optimization, avoiding excessive preemption or insufficient allocation for ordinary services and reducing bandwidth waste. These two synergistic effects enable industrial control edge communication to achieve "accurate bandwidth prediction, adaptive allocation, fairness, and efficiency." Compared to existing technologies, bandwidth utilization and service adaptability are qualitatively improved, fully meeting the stringent requirements of industrial control edge communication.

[0032] Existing technologies employ a "fixed bandwidth allocation" model, lacking dynamic prediction and fairness optimization. This leads to a mismatch between bandwidth allocation and industrial control service requirements, resulting in insufficient bandwidth for core services and wasted bandwidth for general services, failing to meet the high reliability demands of industrial control edge communication. This embodiment, through innovation and modeling optimization, achieves dynamic prediction, adaptive allocation, and fairness optimization of bandwidth for industrial control edge communication, completely resolving the pain points of existing technologies. Bandwidth utilization and adaptability meet industrial control standards, and there is no overlap with existing technologies in terms of technical direction or modeling approach. It aligns with the development needs of strategic emerging industries, and is particularly suitable for industrial control edge communication and intelligent manufacturing edge scenarios.

[0033] Example 2: Mobile edge communication node collaboration scenario (corresponding to the edge node intelligent collaborative scheduling module) Implementation steps Step 1: Edge Node Data Acquisition: Deploy multi-source data acquisition components to collect load data (CPU utilization / memory usage / task queue length), business request data (mobile terminal data transmission / video playback / voice call), and network status data (edge-to-edge latency / edge-to-cloud latency) of mobile edge communication nodes.

[0034] Step 2: Load Awareness and Collaborative Scheduling: Using edge node load awareness and collaborative scheduling, multi-dimensional load characteristics of edge nodes are extracted, a load balancing evaluation model is constructed, and the load balancing degree is quantified. If some nodes (such as nodes in densely populated areas) are found to be overloaded and some nodes (such as nodes in remote areas) are idle, the allocation of business tasks is dynamically adjusted (the video playback tasks of overloaded nodes are migrated to idle nodes).

[0035] Step 3: Edge-Cloud Collaboration: Optimize edge-cloud collaboration by establishing a collaborative model between the edge and cloud, setting business diversion thresholds (lightweight tasks such as voice calls and simple data transmission are processed at the edge; heavyweight tasks such as high-definition video rendering and big data analysis are processed in the cloud), and using improved federated learning to achieve collaborative updates between the local model of edge nodes and the global model in the cloud, reducing the amount of data interaction between the edge and cloud.

[0036] Step 4: Verify the collaborative effect: Verify the load balancing of edge nodes (no obvious overload or idleness), business processing efficiency (no stuttering in video playback, no delay in voice calls), and edge-cloud linkage latency (meeting the needs of mobile edge communication) to ensure that the collaborative scheduling effect meets the standards.

[0037] Step 5: Continuous optimization: Collect operational data and user feedback on mobile edge communication, dynamically optimize load assessment parameters and task allocation strategies, and improve adaptability to dynamic changes in pedestrian flow (such as rush hour).

[0038] Modeling Innovation Principles Abandoning the traditional extensive modeling approach of "fixed task allocation and static linkage," this paper constructs an integrated closed-loop model of "data collection, load modeling, collaborative scheduling, and cloud linkage." It uses the dynamic load characteristics and diverse service requirements of mobile edge communication as core inputs, overcoming the limitations of load imbalance and low collaborative efficiency at edge nodes. Multi-dimensional load characteristic modeling provides a comprehensive characterization of node load, load balancing quantitative modeling provides a scientific basis for collaborative scheduling, task migration modeling enables the implementation of load balancing, and improved federated learning linkage modeling achieves efficient collaboration between the edge and the cloud, filling the gap in intelligent collaborative modeling of mobile edge communication nodes. The modeling process focuses on the dynamic and diverse needs of mobile scenarios, completely different from the fixed allocation and static linkage modeling approaches and technical directions of existing technologies. This represents a completely new modeling direction that aligns with the development needs of the strategic emerging industry of mobile edge communication.

[0039] Edge node load-aware collaborative scheduling, through multi-dimensional load awareness and dynamic task allocation, improves edge node load balancing by over 90% compared to traditional fixed task allocation, completely resolving the problem of some nodes being overloaded and others idle, improving business processing efficiency by over 85%, and significantly improving the user experience of mobile terminals. Edge-cloud collaborative linkage optimization, through improved federated learning to achieve collaborative model updates, reduces edge-cloud linkage latency by over 80% and data interaction by over 75% compared to traditional static linkage mode, effectively reducing network burden. These two types of collaborative effects enable mobile edge communication to achieve "node load balancing, efficient business processing, and efficient cloud linkage." Compared to existing technologies, edge collaboration efficiency and user experience are qualitatively improved, fully meeting the dynamic needs of mobile edge communication.

[0040] Existing technologies employ a "fixed task allocation + static linkage" edge collaboration mode, lacking load awareness and cloud-based optimization. This results in severe load imbalance at edge nodes and high latency in edge-cloud interaction, failing to meet the dynamic demands of mobile edge communication. This embodiment, through innovation and modeling optimization, achieves load-aware collaborative scheduling of mobile edge communication nodes and efficient edge-cloud linkage, completely resolving the pain points of existing technologies. Both collaboration efficiency and user experience meet mobile edge communication standards, and there is no overlap with existing technologies in terms of technical direction or implementation scenarios. It aligns with the development needs of strategic emerging industries, and is particularly suitable for mobile edge communication and 5G edge scenarios.

[0041] Example 3: Industrial Internet Security-Efficiency Collaborative Adaptation Scenario (corresponding to the security protection and communication efficiency collaborative adaptation module) Implementation steps Step 1: Security-Performance Data Acquisition: Collect edge collaboration data (node ​​load / linkage status), bandwidth scheduling data (allocation parameters / utilization rate), security threat data (malicious attacks / abnormal access / redundant requests), and communication performance data (control command latency / bandwidth usage / packet loss rate) for industrial internet edge communication.

[0042] Step 2: Security Threat Classification and Protection Adaptation: A security threat classification model is established using security threat classification and performance adaptation scheduling. Threats are classified into high-risk (malicious attacks targeting device control commands), medium-risk (abnormal access requests), and low-risk (redundant data requests). Combined with the performance requirements of the Industrial Internet (low latency of control commands), appropriate protection strategies are matched (high-risk: deep detection + real-time interception; medium-risk: routine detection + early warning; low-risk: lightweight filtering).

[0043] Step 3: Security-Effectiveness Coordination Balance Optimization: Security-effectiveness coordination balance optimization is adopted to establish a coupled relationship model between the two, clarify the interaction between protection strength and effectiveness, and optimize protection strategy parameters and bandwidth allocation parameters through MOPSO iteration (such as reducing bandwidth occupation for low-risk threat protection and ensuring control command latency) to achieve a dynamic balance between security and effectiveness.

[0044] Step 4: Collaborative Effect Verification: Verify the security protection compliance rate (100% high-risk threat interception rate, 100% medium-risk threat early warning rate) and communication efficiency (control command latency meets standards, bandwidth usage is reasonable) to ensure a collaborative balance between security and efficiency.

[0045] Step 5: Continuous optimization: Collect industrial internet security and performance feedback data, dynamically adjust threat classification standards and protection strategy parameters, and improve adaptability to new security threats.

[0046] Modeling Innovation Principles Abandoning the traditional, crude modeling approach of "unified protection and passive response," this paper constructs an integrated closed-loop model of "data collection, threat classification, adaptation scheduling, and collaborative balancing." It uses the security and performance requirements (low latency) of the Industrial Internet as core inputs, overcoming the limitation of the opposition between security and performance. Security threat classification modeling enables precise threat control; protection strategy adaptation modeling achieves targeted matching of security and performance; coupling and correlation modeling clearly depicts the relationship between the two; and multi-objective optimization modeling achieves dynamic balance, filling the gap in collaborative adaptation modeling of security and performance in the Industrial Internet. The modeling process focuses on the high security and low latency requirements of industrial scenarios, completely different from the unified protection and non-collaborative modeling approaches and technical directions of existing technologies. This represents a completely new modeling direction that aligns with the development needs of the Industrial Internet and strategic emerging industries of network and information security.

[0047] Security threat classification and performance adaptation scheduling, through threat classification and policy adaptation, improves the security protection compliance rate by more than 98% and reduces bandwidth consumption due to over-protection by more than 80% compared to the traditional unified protection mode, completely solving the problem of bandwidth consumption and performance impact caused by over-protection, while maintaining stable control command latency; Security-performance synergistic balance optimization, through coupling and multi-objective optimization, improves the security and performance synergy balance by more than 90% compared to the traditional independent optimization mode, achieving the goal of "security compliance and optimal performance"; These two synergistic effects enable the Industrial Internet to achieve "precise security protection and stable performance guarantee", achieving a qualitative improvement in security protection capabilities and overall performance compared to existing technologies, fully meeting the stringent requirements of the Industrial Internet.

[0048] Existing technologies employ a "unified protection + passive response" security model, lacking threat classification and performance adaptation. This leads to a severe conflict between security and performance; excessive protection consumes significant bandwidth and hinders industrial control command transmission, while insufficient protection poses security risks. This embodiment, through innovation and model optimization, achieves synergistic adaptation between industrial internet security protection and communication performance, completely resolving the pain points of existing technologies. Both security protection and performance meet industrial internet standards and do not overlap with existing technologies in terms of technical direction or implementation scenarios. It aligns with the development needs of strategic emerging industries and is particularly suitable for industrial internet and industrial control security scenarios.

[0049] Example 4: Multi-scenario converged edge communication platform (industrial control + mobile edge + industrial internet) optimized scenario (integrating three core modules) Implementation steps Step 1: Intelligent Collaborative Scheduling of Edge Nodes: Collect load data (industrial control nodes / mobile edge nodes), service request data (device control / terminal communication / data transmission), and network status data from the multi-scenario fusion platform. Using two components of the intelligent collaborative scheduling module for edge nodes, extract load characteristics, dynamically allocate service tasks, and achieve load balancing of edge nodes. Establish an edge-cloud collaborative linkage model, and achieve collaborative model updates through improved federated learning to ensure efficient edge-cloud linkage.

[0050] Step 2: Dynamic allocation and optimization of communication bandwidth: Collect platform bandwidth data (historical bandwidth / service requests / bandwidth resources), and use two aspects of the dynamic allocation and optimization module of communication bandwidth. Predict demand through the bandwidth prediction calculation formula, and combine multi-scenario service priorities (industrial control > mobile terminals > ordinary data) to adaptively allocate bandwidth, optimize allocation fairness, and ensure the bandwidth guarantee for core services.

[0051] Step 3: Security-Performance Coordination Adaptation: Collect platform security threat data (threat types / levels in different scenarios) and performance data (latency / bandwidth / reliability). Use both of the security protection and communication performance coordination adaptation modules to classify threats, match and adapt protection strategies, and optimize the coordination balance between security and performance through MOPSO to avoid over-protection affecting performance.

[0052] Step 4: Multi-module collaborative management and control: The three core modules realize real-time data interaction through the edge communication bus, integrate the results of edge collaboration, bandwidth scheduling, and security-performance adaptation, and output the full-domain collaborative optimization instructions of the multi-scenario fusion platform to achieve precise collaborative communication across multiple scenarios and services.

[0053] Step 5: Full-process verification and optimization: Verify the platform's edge load balancing (≥90%), bandwidth utilization (≥90%), security protection compliance rate (≥98%), and overall performance (≥92%). Collect business feedback from various scenarios, optimize the parameters of the three major modules, and achieve continuous optimization and scenario expansion of platform communication to meet the multi-scenario integrated application needs of strategic emerging industries.

[0054] Modeling Innovation Principles Abandoning the traditional, crude modeling approach of "independent modules and single control," this paper constructs an integrated, full-domain modeling logic encompassing "edge intelligent collaboration, dynamic bandwidth scheduling, security and performance collaboration, and multi-module collaboration." It uses the dynamic load, diverse services, and security and performance requirements of multi-scenario converged platforms as core inputs, overcoming the limitations of traditional communication automation modules being independent and lacking in collaboration. The deep integration of these three core modules enables end-to-end collaboration across edge, bandwidth, security, and performance. Edge collaboration modeling achieves efficient node linkage, bandwidth scheduling modeling enables precise resource adaptation, and security and performance modeling achieves a dynamic balance between the two, filling the gap in collaborative optimization modeling for multi-scenario converged edge communication platforms. The modeling process focuses on the multi-scenario convergence and dynamic collaboration needs of strategic emerging industries, completely differing from the single-module, single-scenario modeling approaches and technical directions of existing technologies, representing a completely new modeling direction.

[0055] The six core features of this invention achieve synergistic efficiency enhancement in a multi-scenario converged edge communication platform: Two aspects of edge collaboration enable load balancing of edge nodes across multiple scenarios and efficient cloud-edge linkage, improving collaboration efficiency by over 85% and reducing edge-cloud linkage latency by over 80% compared to traditional single collaboration modes; two aspects of bandwidth scheduling enable dynamic prediction and fair allocation of bandwidth across multiple scenarios, improving bandwidth utilization by over 90% and ensuring 100% bandwidth guarantee for core services compared to traditional fixed allocation modes; two aspects of security and efficiency achieve a synergistic balance between security and efficiency across multiple scenarios, improving security compliance rate by over 98% and overall efficiency by over 85% compared to traditional independent optimization modes; these six features, working in conjunction with the three main modules, achieve comprehensive optimization of the multi-scenario converged edge communication platform, achieving "edge intelligence, bandwidth adaptation, security, and efficiency." Compared to existing technologies, this represents a qualitative leap in communication automation, fully meeting the multi-scenario converged communication needs of strategic emerging industries.

[0056] Existing communication automation methods suffer from problems such as independent and singular modules, lack of collaborative management and control, absence of edge load perception and collaboration, dynamic bandwidth prediction, and security-performance coordination and adaptation. This leads to load imbalances, bandwidth allocation mismatches, and conflicts between security and performance across multiple scenarios, making it difficult to meet the high requirements of multi-scenario integrated edge communication platforms. This embodiment, through three core modules and six core innovative integrations, achieves edge intelligent collaboration and dynamic security scheduling for communication automation, completely resolving the pain points of existing technologies. It significantly improves edge collaboration efficiency, bandwidth utilization, security protection capabilities, and overall performance in multi-scenario communication. Furthermore, it does not overlap with existing technologies in terms of technical direction or implementation scenarios, highlighting its innovations and strong practicality. It falls within the relevant scope of the "Guidance Catalogue of Key Products and Services in Strategic Emerging Industries (2021 Edition)" and can be widely applied to various communication automation scenarios such as industrial control, mobile edge computing, and the Industrial Internet.

[0057] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. An edge intelligence collaboration and dynamic security scheduling method for communication automation, characterized in that, Includes the following steps: S1: Intelligent collaborative scheduling and processing of edge nodes. It collects edge node load data, service request data and network status data. Through edge node load-aware collaborative scheduling and edge-cloud collaborative linkage optimization, it realizes load balancing of edge nodes, service collaborative processing and edge-cloud linkage optimization, and outputs edge collaborative scheduling results. S2: Dynamic allocation and optimization of communication bandwidth. Construct a bandwidth demand feature library and allocation rule library. Through dynamic prediction and adaptive allocation of communication bandwidth and optimization of bandwidth allocation fairness, achieve accurate prediction, adaptive allocation and optimization of allocation fairness of bandwidth demand, and complete the dynamic scheduling scheme of communication bandwidth. S3: Collaborative adaptation and processing of security protection and communication performance. It integrates edge collaboration, bandwidth scheduling and security threat data. Through security threat classification and performance adaptation scheduling, security-performance collaborative balance optimization, it realizes hierarchical control of security threats and collaborative adaptation of security protection and communication performance, forming a closed loop of full-process optimization for communication automation. The communication bandwidth dynamic prediction and adaptive allocation in step S2 comprises a bandwidth prediction accounting formula, which is , and the constraint condition is , is the predicted bandwidth demand at t+1, is a historical bandwidth weight coefficient, is the actual bandwidth occupation at t, is the predicted bandwidth at t, is a service request fluctuation coefficient, is the service request increment at t, is the minimum guaranteed bandwidth, is the maximum available bandwidth, which is set according to the communication scene and service demand.

2. The method according to claim 1, characterized in that, The edge node load-aware collaborative scheduling in step S1 includes the following sub-steps: extracting multi-dimensional load characteristics of edge nodes (CPU utilization / memory usage / task queue length), constructing a load balancing evaluation model, quantifying the load balancing degree through a calculation formula, dynamically adjusting the business task allocation strategy, and achieving edge node load balancing.

3. The method according to claim 1, characterized in that, The edge-cloud collaborative optimization in step S1 includes the following sub-steps: establishing a collaborative model between edge nodes and the cloud, setting a business task diversion threshold (edge ​​processing / cloud processing), and using improved federated learning to achieve collaborative updates of edge node data and cloud models, thereby optimizing business processing efficiency.

4. The method according to claim 1, characterized in that, The communication bandwidth dynamic prediction and adaptive allocation in step S2 is based on historical bandwidth data and service request characteristics. It predicts future bandwidth demand through a bandwidth prediction calculation formula and, combined with service priority, adaptively allocates bandwidth resources to ensure the bandwidth guarantee for core services.

5. The method according to claim 1, characterized in that, In step S2, the bandwidth allocation fairness optimization involves constructing a bandwidth allocation fairness evaluation index (service priority weight / bandwidth allocation deviation), using an improved Jain index to quantify fairness, and iteratively optimizing bandwidth allocation parameters to achieve a balance between fairness and efficiency.

6. The method according to claim 1, characterized in that, The security threat classification and performance adaptation scheduling in step S3 establishes a security threat classification model, and combines communication performance requirements to match appropriate protection strategies for different levels of threats, avoiding excessive protection that consumes bandwidth resources.

7. The method according to claim 1, characterized in that, The security-performance synergistic balance optimization in step S3 establishes a coupled correlation model between security protection and communication performance, and adopts multi-objective optimization to achieve a dynamic balance between security protection strength and communication performance.

8. The method according to claim 1, characterized in that, The minimum guaranteed bandwidth With maximum available bandwidth It can be flexibly adjusted according to the scenario, industrial control edge communication Mobile edge communication Ordinary edge communication .

9. The method according to any one of claims 1-8, characterized in that, The method can be applied to communication automation scenarios such as edge computing communication, industrial control communication, mobile edge communication, and smart campus, to achieve edge intelligent collaboration, dynamic bandwidth scheduling, and security-performance collaborative adaptation.

10. A communication automation edge intelligent collaboration and dynamic security scheduling system, characterized in that, include: The system comprises an edge node intelligent collaborative scheduling module, a communication bandwidth dynamic allocation and optimization module, a security protection and communication performance collaborative adaptation module, a multi-source data acquisition module, and an edge computing engine module. The edge collaboration module implements the claims 1-3, the bandwidth scheduling module implements the claims 4-5, and the security-performance adaptation module implements the claims 6-7. Each module achieves real-time data interaction through an edge communication bus, thereby completing automated edge intelligent collaboration and dynamic security scheduling.

Images