A system and method for intelligent fault diagnosis and collaborative optimization of resource and energy consumption in communication automation.

Abstract

This invention belongs to the field of communication automation technology and discloses a system and method for intelligent fault diagnosis and collaborative optimization of resource and energy consumption in communication automation. The invention covers the entire process of communication automation from fault diagnosis and resource scheduling to energy consumption optimization by constructing three core modules: intelligent fault diagnosis and tracing, dynamic scheduling and allocation of communication resources, and collaborative optimization and control of communication energy consumption. It employs core technologies such as multi-feature fusion diagnosis of communication faults, reverse reasoning for fault tracing, dynamic resource scheduling and priority adaptation, and collaborative optimization and dynamic control of energy consumption. This overcomes the industry bottlenecks of traditional communication automation, such as "lagging fault diagnosis, extensive resource scheduling, and a disconnect between energy consumption and efficiency." It achieves accurate fault diagnosis and rapid tracing, dynamic adaptation and efficient utilization of communication resources, and collaborative optimization and precise control of communication energy consumption. This significantly improves the reliability, resource utilization, and energy consumption control level of communication networks, adapting to the needs of various scenarios such as industrial communication, backbone network communication, and campus communication. In particular, it solves the technical problems of low fault diagnosis accuracy, resource scheduling and service mismatch, and the conflict between energy consumption optimization and communication efficiency.

Description

Technical Field

[0001] This invention belongs to the field of information technology, specifically relating to a communication automation fault intelligent diagnosis and resource energy consumption collaborative optimization system and method. Background Technology

[0002] In the current field of communication automation, existing technologies have achieved basic applications such as "basic fault monitoring, fixed resource allocation, and simple energy consumption control." However, in complex scenarios involving increased communication network complexity, diversified service requirements, and refined energy consumption management, specific and unresolved practical problems remain for the three sub-scenarios: "accuracy of fault diagnosis," "adaptability of resource scheduling," and "synergy between energy consumption and efficiency." These are all scenario-specific problems, not macro-level challenges, as follows: 1. Insufficient accuracy in fault diagnosis, lack of multi-feature fusion and source tracing: Existing fault diagnosis mostly adopts the "single feature monitoring + manual investigation" mode, lacking multi-feature fusion diagnosis of communication faults, and also lacking a fault source tracing reverse reasoning mechanism; resulting in low fault identification accuracy (easy to misjudge and miss), inability to accurately determine the fault type, and lagging fault source tracing, which can only locate the fault occurrence node, but cannot find the fault root cause and propagation path, resulting in low fault investigation efficiency and easy to cause the fault to escalate.

[0003] 2. Poor resource scheduling adaptability, lack of dynamic scheduling and performance accounting: Existing resource scheduling mostly adopts the "fixed allocation + static adjustment" mode, lacking dynamic scheduling and priority adaptation of communication resources, and also lacking a resource allocation performance accounting mechanism; resulting in a mismatch between resource scheduling and business needs (insufficient high-priority business resources, waste of low-priority business resources), low resource utilization efficiency, and inability to quantify the rationality of resource allocation, with blind scheduling adjustments that cannot adapt to the dynamic changes in business needs.

[0004] 3. Lack of synergy between energy consumption and efficiency, and absence of collaborative optimization and dynamic management: Existing energy consumption control mostly adopts the "fixed threshold control + passive energy saving" mode, lacking collaborative optimization of communication energy consumption, as well as dynamic management and feedback adjustment mechanisms for energy consumption; this leads to a conflict between energy consumption optimization and communication efficiency (excessive energy saving reduces communication efficiency, while ensuring efficiency results in excessive energy consumption), resulting in low precision in energy consumption management and an inability to achieve the synergistic goal of "efficiency meeting standards and optimal energy consumption", which does not meet the needs of green communication development.

[0005] Existing methods for communication automation lack core innovations in "intelligent fault diagnosis and tracing, dynamic resource scheduling and efficiency calculation, and synergistic optimization of energy consumption and efficiency." They are particularly lacking in areas such as multi-feature fusion diagnosis of faults, resource allocation efficiency calculation, and modeling and solving for the coupled balance between energy consumption and efficiency, thus failing to address the aforementioned specific problems. This invention focuses on the development needs of strategic emerging industries (industrial internet, artificial intelligence basic software and hardware), proposing an innovation-driven method for intelligent fault diagnosis and synergistic optimization of resource and energy consumption. This fills the gaps in existing technologies and helps communication automation upgrade towards "intelligent diagnosis, precise scheduling, and green efficiency." Summary of the Invention

[0006] Addressing the three specific problems raised in the background technology, the present invention aims to provide a communication automation fault intelligent diagnosis and resource energy consumption collaborative optimization system and method. This system achieves accurate diagnosis and rapid source tracing of communication faults, dynamic scheduling and efficient utilization of communication resources, and collaborative optimization and precise control of communication energy consumption. It solves the problems of insufficient accuracy in fault diagnosis, poor adaptability of resource scheduling, and lack of synergy between energy consumption and efficiency. The entire process emphasizes innovation and modeling solutions, without involving rules for intellectual activities. This improves the reliability, resource utilization, and energy consumption control level of communication networks, further perfecting the communication automation technology system in complex communication scenarios, and aligns with the development direction of strategic emerging industries and the needs of green communication development.

[0007] The present invention is implemented through the following specific technical solution: (I) Intelligent Diagnosis and Traceability Module for Communication Faults This module is designed to accurately identify, determine the type of, and trace the root cause of communication faults. It constructs an intelligent diagnosis and tracing modeling system for communication faults, solves the problems of low accuracy in fault diagnosis and delayed tracing, improves the efficiency of fault investigation and the reliability of communication networks, and provides a guarantee for the stable operation of automated communication.

[0008] Modeling Approach: Abandoning the traditional extensive modeling approach of "single feature monitoring and manual investigation," we construct an integrated modeling logic of "operational data acquisition - fault feature modeling - multi-feature fusion modeling - fault source tracing modeling - diagnostic verification modeling." Combining the operational characteristics of communication networks (signal / packet loss / delay), fault type characteristics (hardware fault / link fault / protocol fault), and fault propagation patterns, we establish a fault feature library, a fusion diagnostic model, and a source tracing reasoning model. We design multi-feature fusion diagnosis of communication faults and reverse reasoning for fault source tracing to achieve accurate fault diagnosis and rapid source tracing.

[0009] First, deploy multi-source data acquisition components to collect communication network operation data (signal attenuation / data packet loss rate / latency fluctuation / port operating status), fault characteristic data (typical characteristic parameters of various faults), and service interaction data (service interruption status / data transmission anomaly records) to build a fault diagnosis data resource pool. Then, design a multi-feature fusion diagnosis for communication faults, extract multi-dimensional features of communication faults, construct a fault feature fusion model, and use weighted summation to fuse and calculate the multi-dimensional features, quantifying the fault feature matching degree. With the goal of "highest matching degree and lowest false positive rate," iteratively optimize the feature weights to achieve accurate fault identification and type determination. Identify (hardware failure / link failure / protocol failure); design fault tracing and reverse reasoning, establish a fault propagation path model, and analyze the propagation patterns of different types of faults (e.g., link failure leads to signal attenuation and increased packet loss rate at associated nodes). Use an improved Bayesian network to infer the root cause node (e.g., trace back from the fault occurrence node to the link aging node) and propagation path from the fault occurrence node, clarifying the core cause of the fault (e.g., hardware aging / link interference / protocol conflict); construct a fault diagnosis verification model, quantify the fault identification accuracy, tracing accuracy, and troubleshooting efficiency, dynamically optimize parameters, and ensure intelligent fault diagnosis and rapid tracing.

[0010] 1: Multi-feature fusion diagnosis of communication faults To address the problem of "single-feature fault diagnosis and low accuracy" in existing technologies, an integrated model for multi-dimensional fault feature extraction and fusion calculation is constructed to achieve accurate fault identification and type determination, solve the problems of misjudgment and missed judgment, improve diagnostic accuracy, and fill the technical gap in multi-feature fusion diagnosis of communication automation faults.

[0011] 2: Fault tracing and reverse reasoning To address the issues of "lagging fault tracing and inability to pinpoint the root cause" in existing technologies, an integrated model of fault propagation path modeling and improved Bayesian network inference is constructed to achieve rapid location of fault root causes and propagation paths, solve the problem of lagging tracing, and fill the technical gap in reverse reasoning for fault tracing in communication automation.

[0012] (II) Dynamic scheduling and allocation module for communication resources This module is designed to accurately identify, dynamically schedule, and calculate the efficiency of communication resource requirements. It constructs a dynamic scheduling modeling system for communication resources, solves the problems of rigid and poorly adaptable resource scheduling, improves resource utilization and scheduling rationality, and adapts to the dynamic changes in business requirements.

[0013] Modeling Approach: Abandoning the traditional extensive modeling approach of "fixed allocation and static adjustment," we construct an integrated modeling logic of "resource-business data collection-demand identification modeling-dynamic scheduling modeling-performance accounting modeling." Combining communication resource characteristics (bandwidth / computing power / storage), business demand characteristics (priority / resource consumption / real-time performance), and resource constraints, we establish a resource feature library, a dynamic scheduling model, and a performance accounting model. We design dynamic scheduling and priority adaptation of communication resources, as well as performance accounting for resource allocation, to achieve dynamic adaptation and efficient utilization of resources.

[0014] First, a resource feature library and a scheduling rule library are constructed. Communication resource data (total resources / available resources / resource consumption rate), business requirement data (business type / priority / resource requirements / real-time requirements), and resource constraint data (resource allocation ceiling / consumption cost) are collected to build a resource scheduling data resource pool. Then, dynamic scheduling and priority adaptation of communication resources are designed. Businesses are prioritized (core business / important business / ordinary business), and resource requirement characteristics of each business are extracted. Combined with available resources, the resource allocation ratio is dynamically adjusted to prioritize the resource needs of high-priority businesses (e.g., reserving dedicated resources for core businesses), while ordinary businesses share the remaining resources, achieving precise matching between resources and services. A resource allocation efficiency calculation is designed. Through the resource allocation efficiency calculation formula, the rationality and efficiency of resource allocation are quantified (balancing priority satisfaction, resource utilization, and cost control). If the efficiency value is lower than a set threshold, the resource allocation parameters are iteratively optimized (adjusting the resource allocation ratio for each business) to improve resource utilization efficiency. Finally, a resource scheduling verification model is constructed to quantify resource utilization, business requirement satisfaction rate, and efficiency calculation value, dynamically optimizing parameters to ensure dynamic adaptation and efficient utilization of communication resources.

[0015] 3: Dynamic scheduling and priority adaptation of communication resources To address the problem of "fixed resource scheduling and mismatch with services" in existing technologies, an integrated model of service priority modeling and dynamic scheduling adaptation is constructed to achieve precise matching of resources and service needs, solve the problems of resource waste and unmet needs, improve resource utilization, and fill the technical gap in dynamic scheduling and priority adaptation of communication automation resources.

[0016] 4: Resource allocation efficiency accounting To address the problems of "ineffective performance accounting and blind adjustment in resource allocation" in existing technologies, an integrated model of performance accounting formula quantification and parameter optimization is constructed to achieve scientific evaluation of the rationality of resource allocation, solve the problem of directionless scheduling and adjustment, and fill the technical gap in performance accounting of resource allocation in communication automation.

[0017] (III) Communication Energy Consumption Co-optimization and Control Module The core of this module is to achieve precise optimization, dynamic control and feedback adjustment of communication energy consumption, build a collaborative optimization modeling system for energy consumption and efficiency, solve the problem of the contradiction between energy consumption and efficiency, improve the level of precision in energy consumption control, and achieve the synergistic goal of "efficiency meeting standards and optimal energy consumption", which meets the needs of green communication development.

[0018] Modeling Approach: Abandoning the traditional extensive modeling approach of "fixed threshold control and passive energy saving," we construct an integrated modeling logic of "energy consumption-efficiency data collection-coupled correlation modeling-coordinated optimization modeling-dynamic control modeling." By combining communication energy consumption data (equipment energy consumption / link energy consumption / resource energy consumption), communication efficiency data (reliability / latency / packet loss rate), and business requirements, we establish an energy consumption-efficiency coupled correlation model, a collaborative optimization model, and a dynamic control model. We design communication energy consumption collaborative optimization, energy consumption dynamic control, and feedback adjustment to achieve a synergistic balance between energy consumption and efficiency.

[0019] First, integrate fault diagnosis data (fault type / impact range), resource scheduling data (resource allocation parameters / utilization rate), energy consumption monitoring data (energy consumption values / energy consumption fluctuations of various devices / links), and communication performance data (reliability / latency / packet loss rate) to construct an energy consumption-performance data resource pool. Then, design a collaborative optimization for communication energy consumption, establish a coupled correlation model between energy consumption and communication performance, clarify the interaction between energy consumption parameters (such as equipment operating power) and performance indicators (such as communication reliability) (e.g., appropriately reducing the power of non-core equipment without affecting communication performance while reducing energy consumption). Adopt an improved particle swarm optimization approach, focusing on "communication efficiency..." With the goal of "achieving compliance and minimizing energy consumption," we iteratively optimize energy consumption control parameters (such as equipment operating power and link sleep strategies); we design dynamic energy consumption control and feedback adjustment, monitor energy consumption data and communication performance data in real time, compare performance thresholds with energy consumption thresholds, and dynamically adjust energy consumption control parameters (such as maintaining power for core equipment and reducing power for non-core equipment) if energy consumption exceeds the standard or performance declines. Through feedback adjustment mechanisms, we ensure a synergistic balance between energy consumption optimization and communication performance; we construct an energy consumption optimization verification model to quantify the magnitude of energy consumption reduction, communication performance compliance rate, and synergistic balance, and dynamically optimize parameters to ensure coordinated energy consumption optimization and precise control.

[0020] 5: Coordinated Optimization of Communication Energy Consumption To address the problem of "opposition and lack of synergy between energy consumption optimization and efficiency" in existing technologies, an integrated model of energy consumption-efficiency coupling correlation modeling and multi-objective optimization is constructed to achieve a synergistic balance between minimizing energy consumption and achieving efficiency targets, thus resolving the conflict between the two and filling the technical gap in synergistic optimization of energy consumption in communication automation.

[0021] 6: Dynamic energy consumption control and feedback adjustment To address the problem of "static and non-feedback-based energy consumption management" in existing technologies, an integrated model of dynamic management and feedback adjustment is constructed to achieve precise and dynamic energy consumption management, solve the problem of lagging energy consumption management, and fill the technological gap in dynamic management and feedback adjustment of energy consumption in communication automation.

[0022] Beneficial effects 1. Multi-feature fusion diagnosis of communication faults: Abandoning the crude approach of single-feature monitoring, a multi-feature fusion and diagnostic modeling system is constructed. Through multi-feature weighted fusion calculation, the accuracy of fault identification is significantly improved and the false judgment rate is greatly reduced. Focusing on innovation in precise fault diagnosis, it meets the development needs of strategic emerging industries in the industrial internet. 2. Fault tracing and reverse reasoning: Constructing a fault propagation path and reverse reasoning modeling system significantly improves fault tracing efficiency, can quickly locate the root cause and propagation path of the fault, greatly shortens the fault troubleshooting time, and fills the technical gap in fault tracing and reverse reasoning. 3. Dynamic scheduling and priority adaptation of communication resources: Construct a priority modeling and dynamic scheduling adaptation system, which significantly improves resource utilization and greatly enhances the satisfaction rate of business needs, focusing on innovation in precise resource scheduling; 4. Resource allocation efficiency accounting: Construct an efficiency accounting and parameter optimization modeling system, which significantly improves the rationality of resource allocation and greatly enhances the accuracy of scheduling and adjustment, filling the technical gap in resource allocation efficiency accounting; 5. Coordinated optimization of communication energy consumption: Constructing a coupled and multi-objective optimization modeling system, the energy consumption is significantly reduced while ensuring that communication performance meets the standards. Focusing on the coordinated innovation of energy consumption and performance, it meets the needs of green communication development. 6. Dynamic Energy Consumption Control and Feedback Adjustment: A dynamic control and feedback adjustment modeling system is constructed, which significantly improves the level of precision in energy consumption control, achieves a dynamic balance between energy consumption and efficiency, and fills the technological gap in dynamic energy consumption control. Attached Figure Description

[0023] Figure 1 : Workflow diagram of the intelligent diagnosis and tracing module for communication faults Detailed Implementation

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

[0025] Example 1: Dynamic scheduling scenario of backbone network communication resources Implementation steps Step 1: Data Acquisition and Parameter Setting: Collect backbone network communication resource data (total bandwidth / available computing power / storage resources) and service requirement data (core service: backbone network data transmission / important service: voice communication / ordinary service: file download), and set priority weights. Resource constraint data (resource allocation limit / consumption cost) Set a threshold for the optimal allocation efficiency of backbone network communication resources. .

[0026] Step 2: Service Priority Classification and Resource Requirement Identification: Using dynamic scheduling and priority adaptation of communication resources, backbone network services are prioritized (core services > important services > ordinary services), and the resource requirement characteristics of each type of service are extracted (core services require high bandwidth and low latency, while ordinary services have lower bandwidth requirements).

[0027] Step 3: Dynamic Resource Scheduling and Performance Calculation: Based on business priorities and resource requirements, resources are dynamically allocated (dedicated high-bandwidth resources are reserved for core businesses, medium-sized resources are allocated to important businesses, and the remaining resources are shared by ordinary businesses); resource allocation performance calculation is adopted, using the performance calculation formula... Quantify resource allocation efficiency and calculate the resource allocation satisfaction rate for various business operations. With resource usage time .

[0028] Step 4: Scheduling optimization and effect verification: If the performance value Iteratively optimize resource allocation parameters (adjust the allocation ratio of ordinary business resources to reduce waste and improve the resource guarantee of core business); verify resource utilization (no obvious waste), business demand satisfaction rate (no lag in core business), and efficiency value (≥0.9).

[0029] Step 5: Continuous optimization: Collect resource usage data and service feedback from backbone network communication, dynamically adjust service priority weights and performance thresholds, and improve adaptability to sudden traffic surges in backbone network services.

[0030] Modeling Innovation Principles Abandoning the traditional extensive modeling approach of "fixed resource allocation and no performance accounting," this paper constructs an integrated closed-loop model of "data acquisition - priority modeling - dynamic scheduling - performance accounting," which addresses the high reliability resource requirements of backbone network communication. Using business priority characteristics as core input, this approach overcomes the limitations of rigid and poorly adaptable resource scheduling. Business priority modeling enables targeted resource allocation, dynamic scheduling modeling achieves precise matching between resources and services, performance accounting formula modeling enables quantitative evaluation of the rationality of resource allocation, and parameter optimization modeling achieves continuous improvement in scheduling effectiveness, filling the gap in dynamic scheduling and performance accounting modeling of backbone network communication resources. The modeling process focuses on the high reliability and high bandwidth requirements of the backbone network, which is completely different from the fixed allocation and non-performance accounting modeling ideas and technical directions 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 scheduling and priority adaptation of communication resources, through service priority classification and dynamic resource allocation, significantly improves resource utilization compared to the traditional fixed allocation mode, achieving a 100% guarantee rate for core business resources and completely solving the problems of resource mismatch and insufficient core business resources. Resource allocation efficiency accounting, through quantification of efficiency accounting formulas and parameter optimization, significantly improves the rationality of resource allocation and greatly enhances the accuracy of scheduling adjustments compared to scheduling modes without efficiency accounting, avoiding resource waste and allocation imbalance. The synergistic effect of these two types of technologies enables backbone network communication to achieve "precise resource scheduling, scientific efficiency evaluation, and efficient and rational utilization." Compared to existing technologies, resource utilization and service adaptability have achieved a qualitative improvement, fully meeting the high reliability and high bandwidth requirements of backbone network communication.

[0032] Existing technologies employ a "fixed resource allocation" model, lacking dynamic scheduling and performance evaluation. This leads to a mismatch between resource allocation and backbone network service demands, resulting in insufficient bandwidth for core services and wasted resources for ordinary services. Furthermore, the rationality of resource allocation cannot be quantified, and scheduling adjustments are often arbitrary, failing to meet the high requirements of backbone network communication. This embodiment, through innovation and modeling optimization, achieves dynamic scheduling and performance evaluation of backbone network communication resources, completely resolving the pain points of existing technologies. Both resource utilization and performance meet backbone network communication standards, and there is no overlap with the technical direction or modeling approach of existing technologies. It aligns with the development needs of strategic emerging industries and is particularly suitable for backbone network and core network communication scenarios.

[0033] Example 2: Intelligent Diagnosis and Source Tracing of Industrial Communication Faults (corresponding to the Intelligent Diagnosis and Source Tracing Module for Communication Faults) Implementation steps Step 1: Fault Diagnosis Data Acquisition: Deploy multi-source data acquisition components to collect operational data of the industrial communication network (signal attenuation / data packet loss rate / latency fluctuation value / device port status), fault characteristic data (typical characteristics of hardware failure / link failure / protocol failure), and service interaction data (abnormal transmission of equipment control commands / data interruption records).

[0034] Step 2: Multi-feature fusion diagnosis of faults: Multi-feature fusion diagnosis of communication faults is adopted to extract multi-dimensional features of faults (such as abnormal port status and signal attenuation corresponding to hardware faults, and increased packet loss rate and latency fluctuations corresponding to link faults), construct a fault feature fusion model, and perform fusion calculation on multiple features by weighted summation to quantify the fault feature matching degree and accurately identify the fault type (such as determining it to be a link fault).

[0035] Step 3: Fault Source Tracing and Reverse Reasoning: Using fault source tracing and reverse reasoning, an industrial communication fault propagation path model is established (e.g., link failure will lead to signal attenuation and data packet loss in related devices). Using an improved Bayesian network, the fault source node (e.g., a node with abnormal data packet loss) is traced backward to locate the root cause node (e.g., an aging link) and the propagation path, and the cause of the fault (link aging) is clarified.

[0036] Step 4: Verification of diagnostic effectiveness and troubleshooting: Verify the accuracy of fault identification (no missed or false cases) and the accuracy of source tracing (precisely locate the root cause), and handle the fault based on the source tracing results (replace aging links); collect fault handling feedback data and optimize feature weights.

[0037] Step 5: Continuous optimization: Collect operational data and fault records of industrial communication networks, dynamically update the fault feature database, optimize inference parameters, and improve the ability to diagnose and trace new types of faults (such as protocol conflict faults).

[0038] Modeling Innovation Principles Abandoning the traditional, crude modeling approach of "single feature monitoring and manual investigation," this paper constructs an integrated closed-loop model encompassing "data acquisition, feature modeling, fusion diagnosis, and source tracing reasoning." It uses the fault characteristics, propagation patterns, and business requirements of industrial communication as core inputs, overcoming the limitations of low fault diagnosis accuracy and delayed source tracing. Multi-dimensional fault feature modeling achieves a comprehensive fault characterization, fusion accounting modeling enables precise fault identification, fault propagation path modeling provides a scientific basis for source tracing, and reverse reasoning modeling enables rapid root cause location, filling the gap in intelligent fault diagnosis and source tracing modeling for industrial communication. The modeling process focuses on the high reliability and low fault requirements of industrial scenarios, completely differing from the single-feature, manual source tracing 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 industries of the Industrial Internet.

[0039] Multi-feature fusion diagnosis of communication faults significantly improves fault identification accuracy and greatly reduces false positive and false negative rates compared to traditional single-feature diagnosis methods by fusing and quantifying multi-dimensional features, thus completely solving the problems of false positives and false negatives and significantly improving the accuracy of industrial communication fault diagnosis. Fault tracing and reverse reasoning, through improved Bayesian networks and fault propagation path modeling, significantly improves fault tracing efficiency compared to traditional manual tracing methods, enabling rapid location of fault root causes and propagation paths, greatly shortening fault investigation time and preventing fault escalation. The synergistic effect of these two methods enables industrial communication to achieve "accurate fault identification, rapid tracing, and efficient processing." Compared to existing technologies, fault diagnosis and tracing capabilities have been qualitatively improved, fully meeting the high reliability requirements of industrial communication.

[0040] Existing technologies employ a fault diagnosis model of "single feature monitoring + manual troubleshooting," lacking multi-feature fusion and source tracing. This results in low fault identification accuracy and delayed source tracing, only able to locate the fault occurrence point but unable to find the root cause, leading to low fault troubleshooting efficiency and potentially causing industrial communication interruptions and production stoppages. This embodiment, through innovation and model optimization, achieves intelligent diagnosis and rapid source tracing of industrial communication faults, completely resolving the pain points of existing technologies. Its diagnostic and source tracing capabilities meet industrial communication standards and have 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 industrial communication and intelligent manufacturing communication scenarios.

[0041] Example 3: Campus Communication Energy Consumption Collaborative Optimization Scenario (corresponding to the Communication Energy Consumption Collaborative Optimization and Control Module) Implementation steps Step 1: Energy Consumption and Efficiency Data Collection: Collect fault diagnosis data (fault type / affected area), resource scheduling data (resource allocation parameters / utilization rate), energy consumption monitoring data (energy consumption value / energy consumption fluctuation of campus switches / routers / links), and communication efficiency data (data transmission latency / packet loss rate / reliability within the campus).

[0042] Step 2: Energy Consumption-Efficiency Coupling Modeling: By adopting communication energy consumption collaborative optimization, a coupling relationship model between energy consumption and communication efficiency is established to clarify the interaction between energy consumption parameters (such as switch operating power) and efficiency indicators (such as data transmission reliability), and to distinguish the energy consumption requirements of core equipment (campus backbone switches) and non-core equipment (edge ​​switches).

[0043] Step 3: Energy Consumption Co-optimization and Parameter Adjustment: By improving particle swarm optimization, with the goal of "achieving communication performance standards and minimizing energy consumption", the energy consumption control parameters are iteratively optimized (core equipment maintains normal operating power to ensure performance; non-core equipment appropriately reduces operating power to reduce energy consumption) to avoid excessive energy saving affecting communication performance.

[0044] Step 4: Dynamic Energy Consumption Control and Feedback Adjustment: Dynamic energy consumption control and feedback adjustment are adopted to monitor energy consumption data and communication performance data in real time. If energy consumption exceeds the standard (excessive power of non-core equipment) or performance declines (insufficient power of core equipment), the control parameters are dynamically adjusted; the reduction in energy consumption and the performance compliance are verified.

[0045] Step 5: Continuous optimization: Collect energy consumption and efficiency feedback data of campus communication, dynamically optimize the parameters of the coupling correlation model and optimization parameters, improve the level of energy consumption management and control, and adapt to the dynamic changes of campus communication services.

[0046] Modeling Innovation Principles Abandoning the traditional extensive modeling approach of "fixed threshold control and passive energy saving," this paper constructs an integrated closed-loop model of "data acquisition, coupled modeling, collaborative optimization, and dynamic control." It uses the energy consumption requirements, efficiency requirements, and equipment characteristics of park communication as core inputs, breaking through the limitation of the opposition between energy consumption and efficiency. The coupled modeling of energy consumption and efficiency clearly depicts their relationship; multi-objective optimization modeling achieves synergy between minimizing energy consumption and meeting efficiency standards; dynamic control modeling achieves precise energy consumption control; and feedback adjustment modeling ensures the continuous maintenance of collaborative balance, filling the gap in collaborative optimization modeling of energy consumption and efficiency in park communication. The modeling process focuses on the green and efficient needs of park communication, completely different from the fixed threshold and passive energy-saving 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 green communication.

[0047] Coordinated optimization of communication energy consumption, through coupled correlation modeling and multi-objective optimization, significantly reduces energy consumption compared to traditional passive energy-saving modes, while ensuring communication performance meets standards, completely resolving the conflict between energy consumption and performance, and achieving the goal of "green energy saving and stable performance." Dynamic energy consumption control and feedback adjustment, through real-time monitoring and dynamic adjustment, significantly improves the level of precision in energy consumption control compared to traditional static control modes, and can quickly respond to changes in energy consumption and performance, ensuring a coordinated balance between the two. These two synergistic effects enable park communication to achieve "precise energy consumption optimization, stable performance guarantee, and dynamic and flexible control." Compared to existing technologies, the level of energy consumption control and overall performance have been qualitatively improved, fully meeting the green and efficient needs of park communication.

[0048] Existing technologies employ a "fixed threshold control + passive energy saving" energy consumption control mode, lacking collaborative optimization and dynamic management. This results in a severe conflict between energy consumption and efficiency; excessive energy saving leads to communication bottlenecks and packet loss within the park, while prioritizing efficiency results in excessive energy consumption, failing to achieve green and efficient communication. This embodiment, through innovation and modeling optimization, achieves collaborative optimization and dynamic management of park communication energy consumption and efficiency, completely resolving the pain points of existing technologies. Both energy consumption control and efficiency meet park 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 park communication and smart community communication scenarios.

[0049] Example 4: Multi-scenario converged communication platform (backbone network + industry + park) optimized scenario (integrating three core modules) Implementation steps Step 1: Intelligent Fault Diagnosis and Source Tracing: Collect network operation data, fault feature data, and business interaction data from the multi-scenario fusion platform. Using two components of the intelligent communication fault diagnosis and source tracing module, extract multi-dimensional fault features. Accurately identify fault types through multi-feature fusion calculation. Use reverse reasoning to locate the root cause and propagation path of the fault, and quickly handle various faults (backbone network link faults, industrial equipment faults, and park edge equipment faults).

[0050] Step 2: Dynamic scheduling and allocation of resources: Collect platform resource data and multi-scenario business demand data (backbone network core business, industrial control business, and park general business). Use two components of the communication resource dynamic scheduling and allocation module to prioritize and classify services, dynamically allocate resources, quantify resource allocation efficiency through efficiency calculation formulas, iteratively optimize parameters, and ensure efficient resource utilization and satisfaction of business needs.

[0051] Step 3: Energy Consumption Co-optimization and Control: Collect platform energy consumption data, efficiency data, fault and resource scheduling data, and use two components of the communication energy consumption co-optimization and control module to establish an energy consumption-efficiency coupled correlation model. Through multi-objective optimization, minimize energy consumption and achieve efficiency targets, dynamically control energy consumption parameters, and maintain the coordinated balance between the two through a feedback adjustment mechanism.

[0052] Step 4: Multi-module collaborative management and control: The three core modules realize real-time data interaction through the communication data bus, integrate the results of fault diagnosis, resource scheduling and energy consumption optimization, and output the full-domain collaborative optimization instructions of the multi-scenario fusion platform to achieve precise collaborative communication of multiple scenarios and multiple services, and ensure the stable, efficient and green operation of the platform.

[0053] Step 5: Full-process verification and optimization: Verify the platform's fault diagnosis accuracy, resource utilization, energy consumption reduction, and overall efficiency; collect business feedback from various scenarios; optimize the parameters of the three major modules; achieve continuous optimization and scenario expansion of platform communication; and 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 "intelligent fault diagnosis, dynamic resource scheduling, energy consumption collaborative optimization, and multi-module collaboration." It uses the fault characteristics, resource requirements, energy consumption requirements, and business diversity of multi-scenario converged platforms as core inputs, overcoming the limitations of traditional communication automation modules being independent and lacking coordination. The deep integration of these three core modules achieves full-process collaboration across fault, resource, energy consumption, and efficiency. Fault diagnosis modeling ensures stable platform operation, resource scheduling modeling achieves efficient resource utilization, and energy consumption optimization modeling achieves green and efficient operation, filling the gap in fault-resource-energy consumption collaborative optimization modeling for multi-scenario converged communication platforms. The modeling process focuses on the multi-scenario integration and green efficiency 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 in a multi-scenario converged communication platform: Two fault diagnosis features enable accurate identification and rapid tracing of faults across multiple scenarios, significantly improving diagnostic accuracy and tracing efficiency compared to traditional single fault diagnosis modes, and drastically reducing platform failure rates; two resource scheduling features enable dynamic adaptation and performance calculation of resources across multiple scenarios, significantly improving resource utilization compared to traditional fixed allocation modes, and achieving 100% satisfaction of multi-scenario business needs; two energy consumption optimization features achieve a synergistic balance between energy consumption and performance across multiple scenarios, significantly reducing energy consumption compared to traditional passive energy-saving modes, while ensuring the platform's overall performance meets standards; these six features, working in conjunction with the three main modules, achieve comprehensive optimization of the multi-scenario converged communication platform in terms of "stability, efficiency, greenness, and intelligence," representing a qualitative leap in communication automation compared to existing technologies, 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, and deficiencies in fault-free multi-feature fusion diagnosis, dynamic resource scheduling and efficiency accounting, and energy consumption and efficiency synergistic optimization. Furthermore, they suffer from lagging fault diagnosis in multi-scenario communication, resource allocation mismatch, and the conflict between energy consumption and efficiency, making it difficult to meet the high requirements of multi-scenario integrated communication platforms. This embodiment, through three core modules and six core fusion innovations, achieves intelligent fault diagnosis and resource and energy consumption synergistic optimization in communication automation, completely solving the pain points of existing technologies. It significantly improves the reliability, resource utilization, energy consumption control level, and overall efficiency of multi-scenario communication, and has no overlap with existing technologies or implementation scenarios. Its innovations are prominent, its practicality is strong, and it falls within the relevant scope of the "Guidance Catalogue of Key Products and Services in Strategic Emerging Industries (2021 Edition)," making it widely applicable to various communication automation scenarios such as backbone networks, industry, and industrial parks.

[0058] 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. A method for intelligent fault diagnosis and collaborative optimization of resource and energy consumption in communication automation, characterized in that, Includes the following steps: S1: Intelligent diagnosis and source tracing of communication faults. It collects communication network operation data, fault characteristic data and service interaction data. Through multi-feature fusion diagnosis of communication faults and reverse reasoning of fault source tracing, it realizes accurate identification, type determination and root cause tracing of communication faults, and outputs fault diagnosis and source tracing results. S2: Dynamic scheduling and allocation of communication resources. Construct a resource feature library and scheduling rule library. Through dynamic scheduling and priority adaptation of communication resources and performance accounting of resource allocation, achieve accurate identification, dynamic scheduling and performance accounting of resource needs, and complete the dynamic allocation scheme of communication resources. S3: Communication energy consumption collaborative optimization and control processing, integrating fault diagnosis, resource scheduling and energy consumption monitoring data, through communication energy consumption collaborative optimization, dynamic energy consumption control and feedback adjustment, to achieve precise optimization, dynamic control and feedback adjustment of energy consumption, forming a closed loop of full-process optimization of communication automation; The resource allocation efficiency calculation in step S2 includes an efficiency calculation formula, which is as follows: The constraints are , Assign performance values ​​to resources. The priority weight for the i-th type of business. The resource allocation satisfaction rate for the i-th type of business. The resource consumption cost for the i-th type of business. Let i be the resource usage duration for the i-th type of service. The threshold for qualified resource allocation efficiency is set according to the communication scenario and business requirements.

2. The method according to claim 1, characterized in that, The multi-feature fusion diagnosis of communication faults in step S1 includes the following sub-steps: extracting multi-dimensional features of communication faults (signal attenuation / data packet loss rate / delay fluctuation value), constructing a fault feature fusion model, and achieving accurate identification and type determination of faults through multi-feature weighted fusion calculation.

3. The method according to claim 1, characterized in that, The fault tracing and reverse reasoning in step S1 includes the following sub-steps: establishing a fault propagation path model, using an improved Bayesian network, reasoning backward from the fault occurrence node to the fault root cause node and propagation path, and clarifying the core cause of the fault.

4. The method according to claim 1, characterized in that, The dynamic scheduling and priority adaptation of communication resources in step S2 dynamically adjusts the resource allocation ratio based on service priority and resource demand characteristics, prioritizing the resource needs of high-priority services and achieving precise matching between resources and services.

5. The method according to claim 1, characterized in that, The resource allocation efficiency calculation in step S2 quantifies the rationality and efficiency of resource allocation through the efficiency calculation formula. If the efficiency value is lower than the threshold, the resource allocation parameters are iteratively optimized to improve resource utilization efficiency.

6. The method according to claim 1, characterized in that, The communication energy consumption collaborative optimization in step S3 establishes a coupled correlation model between energy consumption and communication performance, and adopts improved particle swarm optimization to achieve energy consumption minimization optimization while ensuring that communication performance meets the standards.

7. The method according to claim 1, characterized in that, The energy consumption dynamic control and feedback adjustment in step S3 involves real-time monitoring of energy consumption data and communication performance data, dynamic adjustment of energy consumption control parameters, and ensuring a coordinated balance between energy consumption optimization and communication performance through a feedback adjustment mechanism.

8. The method according to claim 1, characterized in that, The qualified threshold for resource allocation efficiency It can be flexibly adjusted according to the scenario, industrial communication backbone network communication Campus Communications .

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 industrial communication, backbone network communication, park communication, and smart grid communication, to achieve intelligent fault diagnosis, dynamic resource scheduling, and coordinated optimization of energy consumption.

10. A communication automation fault intelligent diagnosis and resource energy consumption collaborative optimization system, characterized in that, include: The system comprises a communication fault intelligent diagnosis and tracing module, a communication resource dynamic scheduling and allocation module, a communication energy consumption collaborative optimization and control module, a multi-source data acquisition module, and an intelligent diagnosis engine module. The fault diagnosis module executes the functions of claims 1-3, the resource scheduling module executes the functions of claims 4-5, and the energy consumption optimization module executes the functions of claims 6-7. Each module achieves real-time data interaction through a communication data bus to complete the intelligent fault diagnosis and collaborative optimization of resource and energy consumption in communication automation.

Images