Substation secondary system communication network adaptive topology reconstruction method

Abstract

The invention provides a substation secondary system communication network adaptive topology reconstruction method, which comprises the following steps: modeling by adopting multi-scale time delay feature fusion, and accurately predicting protocol conversion time delay; designing a hierarchical fusion protocol conversion time delay control framework, wherein the framework comprises two-stage time delay control of feed-forward compensation and feedback adjustment based on a resource-time delay sensitivity matrix; proposing a protocol semantic dynamic cutting technology, and realizing time delay demand-based differential semantic processing through a performance-semantic tradeoff function; and constructing a topology reconstruction decision-making mechanism of end-to-end time delay perception, and comprehensively evaluating the influence of the candidate topology scheme on the key service flow time delay. According to the method, the protocol conversion time delay of key services in the multi-protocol environment of the transformer substation is reduced, and millisecond-level time delay guarantee and self-adaptive optimization of network topology are realized.

Description

Technical Field

[0001] The present invention relates to the secondary system of a substation, in particular to a method for adaptive topology reconstruction of the communication network of the secondary system of a substation. Background Art

[0002] The communication network of the secondary system of a substation, as the core infrastructure of the smart grid, bears various service functions such as protection, control, and measurement, and its performance directly affects the safe and stable operation of the power system. With the in-depth promotion of the construction of the smart grid, the communication network of the secondary system of a substation presents the characteristics of coexistence of multiple protocols, rich service types, and different real-time requirements. Especially in the scenario of cross-protocol service flow transmission, how to ensure the end-to-end transmission delay of delay-sensitive services (such as protection trip signals, emergency control instructions, etc.) has become a key challenge in the design and optimization of the substation communication network.

[0003] At present, the research on the topology optimization of the communication network of the secondary system of a substation mainly focuses on several aspects: the communication network design based on the IEC61850 standard, which focuses on function division and device layout; the highly reliable network architecture based on redundancy technologies, such as HSR (High-Speed Redundancy Protocol) and PRP (Parallel Redundancy Protocol), etc.; the network traffic management based on QoS (Quality of Service), which ensures the transmission of critical service flows through priority scheduling and bandwidth allocation. In the field of protocol conversion, the research mainly focuses on the semantic mapping and data model conversion between different protocols, such as the function mapping and interoperability technologies between IEC 61850 and traditional protocols (Modbus, DNP3.0, etc.). At the same time, the application research of Time-Sensitive Networking (TSN) technology in the power system has also made certain progress, such as the time-aware scheduling based on IEEE 802.1Qbv and the frame replication and elimination technology based on IEEE 802.1CB, etc.

[0004] However, the existing technologies have obvious deficiencies in optimizing the cross - protocol service latency in the multi - protocol environment of substations. In the secondary system of substations, when control commands and protection signals need to be transmitted across protocols (such as from IEC 61850 to DNP3.0), the standard protocol conversion process introduces an uncertain latency ranging from 2 to 10 milliseconds. Especially for critical protection services (such as over - current protection tripping commands), the additional latency introduced by protocol conversion may cause protection actions to be delayed, threatening equipment safety. First, at the protocol conversion level, existing technologies mostly adopt static mapping mechanisms, which cannot perceive the latency sensitivity differences of different service flows, resulting in the inability of critical protection signals to obtain differential processing during protocol conversion, and the conversion latency fluctuates within a large range. Second, the semantic processing during the protocol conversion process usually adopts an "all - or - nothing" processing strategy, either converting all fields completely (ensuring semantic integrity but with a high latency), or adopting an extremely minimalist conversion mode (sacrificing non - critical information in exchange for low latency), lacking the ability to dynamically adjust the semantic retention level according to latency requirements. Currently, there is a lack of a protocol conversion mechanism that can accurately compensate for latency based on the message latency sensitivity, and it is impossible to ensure the real - time requirements of millisecond - level critical services during cross - protocol transmission. Summary of the Invention

[0005] The object of the invention is to provide a method for adaptive topology reconstruction of the communication network in the secondary system of substations, in order to solve at least one technical problem existing in the existing technologies.

[0006] Technical solution: A method for adaptive topology reconstruction of the communication network in the secondary system of substations includes: Collect the communication data of the multi - protocol network in the secondary system of substations, extract multi - scale latency sensitivity features, and construct a multi - scale latency feature model; Use the multi - scale latency feature model to predict the protocol conversion latency and generate a latency compensation strategy for latency - sensitive services; Execute protocol conversion optimization and latency control according to the latency compensation strategy, obtain the optimized conversion result and real - time processing latency, and perform end - to - end latency perception analysis in combination with the multi - scale latency feature model to generate and execute the optimal topology reconstruction plan.

[0007] According to one aspect of the present application, constructing a multi - scale latency feature model includes: Collect the communication data of the multi - protocol network in the secondary system of substations, including the packet timestamps, payload sizes, priority tags, and network device status information of different protocols, and generate an original communication data set; Based on the original communication data set, sequentially extract macro, meso, and micro latency features to obtain macro and meso load feature vectors, and micro - processing feature vectors, and construct a multi - scale latency feature model accordingly.

[0008] According to one aspect of the present application, a multi-scale delay feature model is constructed, including: Extract the baseline load trend and periodic fluctuation components from the macro load feature vector; Read the meso load feature vector, calculate its deviation from the baseline load trend, obtain the load fluctuation intensity and load mutation frequency indicators; and accordingly construct a switching model for high and low load states to form a load state transition matrix; Based on the micro processing feature vector, perform distribution fitting to obtain the delay probability distribution model for each processing stage and combine it with the load state transition matrix to construct a conditional delay distribution model considering state transition; Integrate the baseline load trend, periodic fluctuation components and conditional delay distribution model into a multi-scale delay feature model.

[0009] According to one aspect of the present application, a delay compensation strategy for delay-sensitive services is generated, including: Receive communication data, extract the multi-scale delay features in the current network state and input them into the multi-scale delay feature model to obtain the expected protocol conversion delays of different types of messages under the current network conditions; Based on the expected protocol conversion delay and the end-to-end delay requirement of the message, calculate the delay margin; According to the delay margin and the network resource status, generate a feedforward compensation strategy for high-priority messages with a delay margin less than the threshold to form a delay compensation strategy.

[0010] According to one aspect of the present application, a delay compensation strategy is formed, including: Read the delay margin and priority mark of the message, and classify the message into high, medium and low sensitivities; For high-sensitivity messages, calculate the minimum processing resource requirements required to ensure that their conversion delay does not exceed the delay margin; According to the current system resources and the contribution weights of each resource to reducing the conversion delay, construct a resource-delay sensitivity matrix and calculate the optimal resource allocation scheme; accordingly, combined with the protocol type, message complexity and minimum processing resource requirements of the message, select the most suitable conversion path selection; Integrate the resource allocation scheme and conversion path selection to generate a complete delay compensation strategy.

[0011] According to one aspect of the present application, an optimized conversion result is obtained, including: According to the delay compensation strategy, determine a suitable protocol conversion processing mode for each message to form a conversion mode decision and calculate the allowable processing time; Acquire and analyze the protocol structure of the target message, and identify the key semantic set and the non-key semantic set in the message accordingly; calculate the processing time of the key semantic set and the remaining time budget for processing the non-key semantic set in combination with the allowed processing time; Based on the remaining time budget, an important reserved subset is extracted from the non-critical semantic set, and combined with the critical semantic set to generate a semantic pruning scheme; Protocol conversion is performed according to the semantic tailoring scheme, key semantic sets are prioritized, and optimized conversion results are generated.

[0012] According to one aspect of the present application, identifying a key semantic set and a non-key semantic set in a message includes: Read the protocol type and message type of the target message, and extract the complete semantic structure diagram of the message of this type; According to the current business scenario and control requirements, identify the necessary functional fields from the complete semantic structure diagram; Analyze the application context of the target message in the current business environment and identify the associated status fields required for interaction with other systems from the complete semantic structure diagram; The necessary function fields and associated status fields are combined to form the key semantic set of the message and assign weights, and the remaining fields in the complete semantic structure diagram are classified into the non-key semantic set.

[0013] According to one aspect of the present application, generating a semantic clipping solution includes: Based on the semantic importance scores in the key semantic set and the estimated processing time of each field, a performance-semantics trade-off function is constructed to maximize the amount of semantic information retained under time constraints. Call the performance-semantics trade-off function to select the most important subset from the non-critical semantic set so that its processing time does not exceed the remaining time budget, and generate the non-critical semantic retention subset; Integrate the key semantic set and the non-key semantic retained subset to form a semantic pruning scheme, which includes all the fields that need to be retained and their processing priorities.

[0014] According to one aspect of the present application, it also includes monitoring the real-time processing delay during the protocol conversion process and performing delay control adjustment: Read the real-time processing delay data of the current protocol conversion process, calculate the deviation from the expected protocol conversion delay, and obtain the delay deviation value; when it exceeds the delay deviation threshold, trigger the feedback adjustment process; Analyze the positive and negative direction and magnitude of the delay deviation value to determine whether the current delay condition is exceeding expectations or resource redundancy; In case of delay exceeding expectations, adjust the semantic pruning plan, streamline the non-critical semantic retention subset, and apply for emergency processing resources; In case of resource redundancy, the non-critical semantic reserved subset is expanded and the excess resources are released.

[0015] According to one aspect of the present application, generating an optimal topology reconstruction scheme includes: Based on the multi-scale delay feature model and real-time processing delay data, identifying the delay bottleneck points and congestion areas in the current network topology, and combining the end-to-end delay requirements of each service flow in the substation to construct a network optimization objective function; Based on the network optimization objective function, generating a set of candidate topology reconstruction schemes, including link adjustment, traffic redistribution, and protocol conversion node deployment strategies; Evaluating the impact of each candidate topology reconstruction scheme on the delay of critical service flows, generating a scheme evaluation result, and selecting the scheme with the highest comprehensive score as the optimal topology reconstruction scheme.

[0016] Beneficial effects: This embodiment realizes high-precision prediction of protocol conversion delay, effectively copes with network load fluctuations, controls the stability of the protocol conversion delay of critical protection services, and reduces the conversion delay fluctuation; it can dynamically adjust the semantic retention level according to the delay sensitivity of different messages, optimize the processing delay to the greatest extent on the premise of ensuring functional correctness, ensure the final integrity of the data, and achieve millisecond-level delay guarantee and adaptive optimization of the network topology. Description of the Drawings

[0017] Figure 1 is a flowchart of the steps of a method for adaptive topology reconstruction of a secondary system communication network in an embodiment of the present application.

[0018] Figure 2 is a flowchart of the steps of extracting multi-scale delay sensitivity features to construct a multi-scale delay feature model in an embodiment of the present application.

[0019] Figure 3 is a flowchart of the steps of constructing a multi-scale delay feature model in an embodiment of the present application.

[0020] Figure 4 is a flowchart of the steps of generating a delay compensation strategy for delay-sensitive services in an embodiment of the present application.

[0021] Figure 5 is a flowchart of the steps of forming a delay compensation strategy in an embodiment of the present application. Detailed Embodiments

[0022] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0023] It should be particularly noted that, for clearly showing the step flow of the present application, serial numbers are marked for each step in the specification. These serial numbers are only for the convenience of description and do not limit the execution order of the steps. In actual operation, according to the technical requirements of the specific implementation scenario, the steps can be executed in an order different from that shown in the specification, and in some cases, parallel processing between steps can also be achieved.

[0024] As Figure 1 shown, a method for adaptive topology reconstruction of a communication network in a substation secondary system includes: Collect communication data of a multi-protocol network in the substation secondary system, extract multi-scale delay sensitivity features, and construct a multi-scale delay feature model; Specifically, the communication data includes packet timestamps, payload sizes, priority tags, and network device status information of different protocols (IEC 61850, DNP3.0, Modbus). At different scales (such as millisecond level, second level, etc.), the delay characteristics of the data are different. Extracting multi-scale delay sensitivity features provides a data basis for subsequent conversion delay prediction and topology reconstruction decision-making.

[0025] Use the multi-scale delay feature model to predict the protocol conversion delay and generate a delay compensation strategy for delay-sensitive services; Specifically, the conversion between different communication protocols may introduce additional delays, such as data format changes or processing times. Through the delay feature model, it is possible to predict in advance how long this conversion process will take. To reduce the impact, a compensation scheme is generated. For example, it may send packets in advance, optimize the transmission path, or adjust network resource allocation to ensure that critical services can run stably and quickly.

[0026] Execute protocol conversion optimization and delay control according to the delay compensation strategy, and obtain the optimized conversion result and the real-time processing delay; Specifically, when transmitting data between different communication protocols, format changes or processing differences may occur. Based on the delay compensation strategy, the protocol conversion process is optimized to reduce unnecessary delays. In order to ensure that key services are not affected by long network delays, the transmission strategy is actively monitored and adjusted. For example, it may prioritize important data packets or dynamically adjust resource allocation to reduce the impact of delays on the business. Protocol conversion delay control combining feedforward and feedback can be implemented, and dynamic tailoring of protocol semantics can be performed at the same time to optimize the conversion delay performance while ensuring key semantics.

[0027] Based on the optimized conversion results, real-time processing delay and multi-scale delay feature model, end-to-end delay perception analysis is performed to generate and execute the optimal topology reconstruction plan.

[0028] Specifically, according to the protocol conversion delay analysis results and end-to-end delay requirements, the network bottleneck is identified, and the optimal network topology reconstruction decision is generated and executed. The reconstruction execution results are obtained to achieve the adaptive topology reconstruction of the substation secondary system communication network.

[0029] like Figure 2 As shown, according to one aspect of the present application, a multi-scale delay feature model is constructed, including: Collect communication data of multi-protocol network in substation secondary system and generate original communication data set; Based on the original communication data set, macro, meso and micro delay features are extracted in sequence to obtain macro and meso load feature vectors and micro processing feature vectors. A multi-scale delay characteristic model is constructed based on macro and meso load characteristic vectors, as well as micro processing characteristic vectors.

[0030] According to one aspect of the present application, obtaining an optimized conversion result includes: According to the delay compensation strategy, determine the appropriate protocol conversion processing mode for each message, form a conversion mode decision, and calculate the allowed processing time; Acquire and analyze the protocol structure of the target message, and identify the key semantic set and the non-key semantic set in the message accordingly; calculate the processing time of the key semantic set and the remaining time budget for processing the non-key semantic set in combination with the allowed processing time; Based on the remaining time budget, an important reserved subset is extracted from the non-critical semantic set, and combined with the critical semantic set to generate a semantic pruning scheme; Protocol conversion is performed according to the semantic tailoring scheme, key semantic sets are prioritized, and optimized conversion results are generated.

[0031] like Figures 3 to 5 As shown in FIG. 1 , in a certain scenario, the processing process of the adaptive topology reconstruction method of the substation secondary system communication network based on delay sensitivity analysis is as follows: Collect multi-protocol network communication data, including packet timestamps, payload sizes, priority tags, and network device status information for different protocols (IEC 61850, DNP3.0, Modbus), and generate an original communication dataset. Extract macroscopic delay features. By analyzing the network traffic fluctuation patterns within a 24-hour period, calculate the average load level and periodic load patterns for each time period, and output a macroscopic load feature vector. Extract mesoscopic delay features. Statistically analyze the network queue status and processing delays within a 100-ms sliding window, calculate the queue occupancy rate, processing delay variance, and burst traffic metrics, and generate a mesoscopic load feature vector. Extract microscopic delay features. Analyze the processing time distribution of each stage (parsing, mapping, repackaging) during a single protocol conversion process, record the processing delays and processing resource consumption for each stage, and output a microscopic processing feature vector. Integrate the macroscopic load feature vector, mesoscopic load feature vector, and microscopic processing feature vector to construct a multi-scale delay feature model. This model captures the key factors affecting protocol conversion delay and their interaction relationships at different time scales. Specifically: Read the macroscopic load feature vector, extract the periodic load pattern and peak load period features therein, and separate the baseline load trend and periodic fluctuation components through waveform decomposition methods; Read the mesoscopic load feature vector, calculate its deviation from the macroscopic baseline load trend, and obtain the load fluctuation intensity and load mutation frequency metrics; Fit the distribution of the processing delays for each stage in the microscopic processing feature vector to obtain a delay probability distribution model for each processing stage; Based on the load fluctuation intensity and load mutation frequency, construct a switching model for high and low load states to form a load state transition matrix; Combine the delay probability distribution model with the load state transition matrix to construct a conditional delay distribution model considering state transitions; Through a hierarchical feature fusion algorithm, integrate the baseline load trend, periodic fluctuation components, and conditional delay distribution model into a multi-scale delay feature model. This model can accurately capture the relationship between network load and protocol conversion delay at multiple time scales.

[0032] Receive a real-time raw communication data set, extract multi-scale delay features under the current network state, input them into a pre-trained multi-scale delay feature model, and predict the expected protocol conversion delays of different types of messages under the current network conditions. Based on the expected protocol conversion delays and the end-to-end delay requirements of the messages, calculate the delay margin and determine whether it is necessary to trigger the delay compensation mechanism. For high-priority messages with insufficient delay margin, generate a feedforward compensation strategy according to the expected protocol conversion delays and the network resource status, including a resource allocation plan and a conversion path selection, and output the delay compensation strategy, specifically: read the delay margin and priority flag of the message, and classify the message into three categories: high-sensitivity, medium-sensitivity, and low-sensitivity based on a preset threshold; for high-sensitivity messages, calculate the minimum processing resources required to ensure that their conversion delays do not exceed the delay margin; according to the currently available processor resources, memory resources, and network bandwidth resources, as well as the contribution weights of each resource to reducing the conversion delay, construct a resource-delay sensitivity matrix; based on the resource-delay sensitivity matrix, use a resource allocation algorithm to calculate the optimal resource allocation plan, which allocates appropriate resources to each high-sensitivity message to maximize the overall delay benefit; according to the allocated resource amount, combined with the protocol type and message complexity of the message, select the most suitable conversion path from a predefined conversion path library, which can provide the minimum conversion delay under resource constraints; integrate the resource allocation plan and the conversion path selection to generate a complete delay compensation strategy, which contains detailed resource allocation instructions and conversion processing flow configurations. Establish a resource pooling mechanism to avoid resource competition problems when multiple high-priority messages arrive simultaneously, pre-allocate processing resources according to the delay compensation strategy, and generate a resource pooling configuration to ensure the resource availability of critical services.

[0033] Based on the conversion path selection in the time delay compensation strategy, determine a suitable protocol conversion processing mode for each message, ranging from a complete protocol stack conversion to a lightweight keyword field conversion, to form a conversion mode decision. Execute two-stage time delay control, implement feedforward scheduling according to the resource allocation plan, prioritize the processing of high time-delay sensitive services, and output resource scheduling instructions. Perform dynamic protocol semantic pruning on messages that require rapid conversion: Analyze the protocol structure of the target message, identify the key semantic set and non-key semantic set therein, specifically: Read the protocol type and message type of the target message, query the pre-built protocol semantic knowledge base, and extract the complete semantic structure diagram of this type of message; According to the current business scenario and control requirements, identify the necessary functional fields in the semantic structure diagram, which are directly related to the realization of the core function of the control command; Analyze the application context of the target message in the current business environment, identify the associated status fields required for interaction with other systems, which are not functional fields but are crucial for the consistency of the system state; Combine the necessary functional fields and associated status fields to form the key semantic set of the message, and classify the remaining fields into the non-key semantic set; Assign semantic importance scores to each field in the key semantic set to reflect its contribution to the realization of business functions. According to the current time delay margin and conversion mode decision, dynamically determine the semantic retention level and generate a semantic pruning plan, specifically: Read the time delay margin and conversion mode decision of the message, and calculate the maximum allowable protocol conversion processing time; Establish a protocol field processing time model to estimate the key semantic processing time required to process all fields in the key semantic set; Compare the maximum allowable processing time with the key semantic processing time. If the key semantic processing time is less than the maximum allowable processing time, calculate the remaining time budget available for processing non-key semantics; Based on the semantic importance scores in the key semantic set and the estimated processing time of each field, construct a performance-semantic trade-off function, which maximizes the retention of semantic information under time constraints; Use the performance-semantic trade-off function to select the most important subset from the non-key semantic set so that its processing time does not exceed the remaining time budget, and generate a non-key semantic retention subset; Integrate the key semantic set and the non-key semantic retention subset to form the final semantic pruning plan, which includes all the fields to be retained and their processing priorities.

[0034] Execute protocol conversion according to the semantic tailoring scheme to ensure the semantic integrity of key control instructions and protection signals, optimize processing delays, and output optimized conversion results. Specifically, read the source protocol message and semantic tailoring scheme, prepare the protocol conversion environment and resources; give priority to processing the fields in the key semantic set, convert them to the target protocol format according to the predefined mapping relationship, and form the key semantic conversion result; if time permits, process the fields in the non-key semantic reserved subset, convert them to the target protocol format, and merge them with the key semantic conversion result; mark the non-key fields that cannot be processed in the current conversion cycle with the to-be-supplemented identifier, record their original information and target mapping relationship, and output them to the to-be-supplemented data cache; assemble the final target protocol message structure, fill in the converted semantic content, and form an optimized conversion result that meets the target protocol specification. Monitor the real-time processing delay in the actual protocol conversion process. When a significant deviation from the expected protocol conversion delay is detected, trigger the feedback adjustment mechanism, dynamically adjust the resource allocation and semantic clipping level, and form a closed-loop control. Specifically, read the real-time processing delay data of the current protocol conversion process, calculate the deviation from the expected protocol conversion delay, and obtain the delay deviation value; set the delay deviation threshold, and when the delay deviation value exceeds this threshold, trigger the feedback adjustment process; analyze the positive and negative directions and amplitudes of the delay deviation value to determine whether the current delay condition is delay exceeding expectations or resource redundancy; for delay exceeding expectations, quickly adjust the semantic clipping plan, further streamline the non-critical semantic retention subset, and form an emergency clipping plan; at the same time, apply for additional emergency processing resources, update the resource allocation plan to an emergency resource plan, and give priority to key semantic processing; for resource redundancy, moderately expand the non-critical semantic retention subset to form an extended clipping plan, and at the same time release excess resources for other messages to use; according to the actual adjustment results, update the parameters of the delay prediction model, improve future prediction accuracy, and output model adjustment parameters. For messages that use semantic clipping, after completing the rapid conversion of key fields, the non-key field information is asynchronously supplemented and transmitted to ensure data integrity while not affecting the real-time performance of key services, and the complete conversion data is output. Specifically, the non-key field information and related metadata in the data cache to be supplemented are read to evaluate the current network load status; based on the network load status and the semantic importance of the data to be supplemented, a hierarchical priority scheduling algorithm is used to calculate the optimal supplementary transmission time window; a dedicated supplementary data packet structure is constructed for the data to be supplemented, which includes metadata such as the original message identifier, timestamp, and supplementary content type to form a supplementary data packet; within the determined supplementary transmission time window, a low-priority channel is used to transmit the supplementary data packet to ensure that the current key business flow is not interfered with; at the target device end, the supplementary data packet is received and associated with the corresponding original conversion message through the message identifier therein; the original conversion message and the supplementary data content are merged to reconstruct the complete protocol message semantics, output the complete conversion data, and update the relevant status in the target system.

[0035] Based on the multi-scale time-delay feature model and real-time processing of time-delay data, identify the time-delay bottleneck points and congestion areas in the current network topology, and output a network bottleneck analysis report. Combine the network bottleneck analysis report with the end-to-end time-delay requirements of each service flow in the substation to construct a network optimization objective function, which balances the time-delay performance of critical services and network resource utilization rate. Specifically: Read the network bottleneck analysis report, extract the bottleneck degree index and congestion duration of each node and link in the network; Analyze the end-to-end time-delay requirements of various service flows in the substation, determine the time-delay tolerance and service importance weight of each type of service; Based on the bottleneck degree index and congestion duration, construct an initial performance evaluation function, which considers the ratio of the time-delay improvement potential to the transformation cost of each bottleneck point, and calculates the node improvement potential score; Use the existing service flow data to construct a network traffic distribution model, simulate the impact of different topology changes on the time-delay of each service flow, and form a topology impact mapping matrix; Integrate the node improvement potential score, topology impact mapping matrix, time-delay tolerance and service importance weight to construct a comprehensive network optimization objective function, which maximizes the time-delay performance gain under multiple constraints (resource limitation, reliability requirement, service continuity). Based on the network optimization objective function, generate a set of candidate topology reconstruction schemes, each scheme includes specific link adjustment, traffic redistribution and protocol conversion node deployment strategies, and output the candidate topology scheme set. Specifically: Based on the existing network topology and network optimization objective function, use the heuristic search algorithm to generate a series of potential topology adjustment schemes to form an initial candidate scheme pool; For each scheme in the candidate scheme pool, refine the specific implementation steps, including link adjustment details, traffic routing rules and conversion node configuration, to form an executable topology adjustment scheme; Conduct a preliminary screening of each topology adjustment scheme, eliminate the obviously unreasonable or overly difficult-to-implement schemes, and retain the high-potential schemes to generate a refined candidate topology scheme set.

[0036] Evaluate the impact of each candidate topology solution in the set on the latency of critical business flows. Considering three dimensions: latency performance, reliability, and implementation complexity, select the solution that can minimize the protocol conversion latency to the greatest extent while meeting the end-to-end latency requirements, and generate the solution evaluation results; select the solution with the highest comprehensive score from the solution evaluation results as the optimal topology reconstruction solution for subsequent network topology reconstruction execution. Specifically: construct a detailed network simulation model that accurately reflects the topology structure, device characteristics, and business flow characteristics of the current substation network; for each solution in the candidate topology solution set, use the simulation model for detailed evaluation, simulate the network performance under different load conditions, and calculate the expected end-to-end latency of each business flow; introduce two additional indicators, reliability score and implementation complexity score, to form a multi-dimensional evaluation system together with the latency performance. Based on factors such as redundancy, single-point failure recovery ability, and security isolation, evaluate the reliability of each solution and generate a reliability score; analyze the implementation difficulty, required resources, and impact on existing services of each solution to generate an implementation complexity score; apply a multi-objective optimization method to conduct a comprehensive evaluation in the three dimensions of latency performance, reliability, and implementation complexity, and calculate a comprehensive optimization score for each solution. Sort the candidate topology solution set according to the comprehensive optimization scores to generate the final solution evaluation results, providing a decision-making basis for selecting the optimal topology reconstruction solution; select the solution with the highest comprehensive optimization score as the optimal topology reconstruction solution, which achieves the best balance in each evaluation dimension. Execute the optimal topology reconstruction solution, adjust the network connections, update the routing table, and reallocate the protocol conversion processing nodes to complete the adaptive reconstruction of the network topology and output the reconstruction execution results.

[0037] Regarding the problem of protocol conversion delay uncertainty, in this embodiment, a multi-scale delay feature fusion model is established to integrate and analyze the delay features at three levels: macroscopic load trend, mesoscopic emergency events, and microscopic processing details, achieving high-precision prediction of protocol conversion delay. Based on the accurate delay prediction, a two-stage delay control strategy is further implemented, combining feedforward resource allocation with real-time feedback adjustment to effectively cope with network load fluctuations and ensure that the protocol conversion delay of critical protection services is stably controlled within 1 millisecond. Regarding the "all-or-nothing" problem of protocol conversion semantic processing, this embodiment proposes a protocol semantic dynamic pruning technology. By accurately identifying the key semantic set and non-key semantic set in the message and introducing a performance-semantic trade-off function, it realizes refined semantic processing based on the delay budget. Breaking the limitation of the traditional dichotomy of "either complete conversion or simplified conversion", it can dynamically adjust the semantic retention level according to the delay sensitivity of different messages, optimizing the processing delay to the greatest extent while ensuring functional correctness. At the same time, through an asynchronous supplementary transmission mechanism, "progressive conversion" is achieved to ensure the ultimate integrity of the data. Existing topology reconstruction methods usually focus on optimizing the traffic distribution at the network level and rarely consider the impact of the deployment of protocol conversion nodes and protocol conversion delay on the overall network performance, resulting in limited end-to-end delay optimization in a multi-protocol hybrid environment. Regarding the problem that topology reconstruction does not consider the impact of protocol conversion delay, this embodiment designs an end-to-end delay-aware topology reconstruction decision-making mechanism, organically combining the deployment of protocol conversion nodes with the optimization of network traffic distribution. By constructing a comprehensive network optimization objective function, not only considering traditional network congestion factors but also particularly focusing on the performance of conversion nodes passed by cross-protocol service flows, it realizes the collaborative optimization of resource allocation, protocol conversion, and network topology. By simulating and evaluating the impact of candidate topology schemes on the delay of critical service flows, a reconstruction scheme that can achieve the best balance in the three dimensions of delay performance, reliability, and implementation complexity is selected, effectively solving the end-to-end delay optimization problem in a multi-protocol hybrid environment.

[0038] In a specific embodiment of the present application, it is applied to a 220 kV intelligent substation. The secondary system of this substation consists of 21 protection and control devices, including 6 protection devices, 4 merging units, 8 intelligent terminals, and 3 gateway devices. These devices use three protocols, namely IEC 61850, Modbus, and DNP3.0, for communication. There is a problem of protocol conversion delay uncertainty in the substation. Especially in cross-protocol services, the delay ranging from 2 to 10 milliseconds introduced by the standard protocol conversion process may cause delays in critical protection services, threatening the safety of the devices. The specific steps include: Step 1: Delay sensitivity data collection and feature extraction.

[0039] 1.1. In this 220 kV substation, network data acquisition devices are deployed to collect network communication data within 24 hours. The acquisition results include the following: IEC 61850 GOOSE messages: 12,463, with an average payload size of 385 bytes; IEC 61850 MMS messages: 8,742, with an average payload size of 512 bytes; DNP3.0 messages: 4,215, with an average payload size of 256 bytes; Modbus messages: 6,834, with an average payload size of 128 bytes. Example of a data packet (partial): Packet ID: PKT - 001254; Timestamp: 2024 - 05 - 09 09:15:23.456; Protocol type: IEC 61850 GOOSE; Payload size: 386 bytes; Priority flag: 7 (highest); Source device: Protection device 1; Destination device: Intelligent terminal 3. These raw data form the original communication data set D raw 。

[0040] 1.2. Analyze the original communication data set D raw for the network traffic fluctuation pattern within a 24 - hour period, and calculate as follows: Average load level L per hour h Calculation formula: L h = ∑(P i × S i ) / T h ; where P i is the i - th data packet, S i is the size of data packet i (bytes), and T h is 1 hour (3,600 seconds). Statistic on the 24 - hour data is performed to obtain the macroscopic load feature vector F macro =[L1, L2,..., L 24 : F macro = [123.5, 142.8, 98.6, 76.4, 68.2, 72.5, 156.8, 254.3, 312.5, 287.6, 265.4, 243.8, 256.9, 278.5, 254.3, 245.6, 267.8, 289.5, 276.4, 232.1, 187.6, 156.4, 134.2, 128.7] KB / s; Periodic load pattern P cycle is extracted through Fourier transform (FFT): P cycle = FFT(F macro ) = [0.0, 124.5∠0°, 78.3∠45°, 45.2∠90°, 32.1∠135°,...] KB / s.

[0041] 1.3. Statistically analyze the network queue status and processing delay within a 100 - ms sliding window: queue occupancy rate Q i Calculate: Q i = B used / B total ; where B used is the occupied buffer size, and B total is the total buffer size. Processing delay variance V i Calculate: V i = sqrt(∑(D j - D avg ) 2 / n); where D j is the processing delay of the j - th data packet, D avg is the average processing delay, and n is the number of data packets within the window. Calculate the burst traffic metric B i : B i = max(R j ) / R avg ; where R j is the data rate at the j - th second within the window, and R avg is the average data rate within the window. Select the statistical results of a representative 100 - ms window (09:15:23.400 - 09:15:23.500): queue occupancy rate Q = 0.65 (65%); processing delay variance V = 0.82ms; burst traffic metric B = 2.34; mesoscopic load eigenvector F meso = [Q, V, B] = [0.65, 0.82, 2.34].

[0042] 1.4. Analyze the processing time distribution in the three stages of parsing, mapping, and repackaging during the protocol conversion process. Taking the conversion from IEC61850 to DNP3.0 as an example: parsing - stage processing delay T parse = 1.25ms; mapping - stage processing delay T map = 1.68ms; repackaging - stage processing delay T pack = 0.92ms. Processing resource consumption statistics: CPU usage rate C cpu = 45%; memory usage M mem = 128MB; number of processing threads N thread = 4. Micro - processing eigenvector F micro = [T parse , T map , T pack , C cpu , M mem , N thread = [1.25, 1.68, 0.92, 45, 128, 4].

[0043] 1.5. Extract macroscopic feature components. Extract the periodic load pattern and peak load period from the macroscopic load feature vector F macro : the baseline load trend BL trend = average value(F macro ) = 203.6 KB / s; the periodic fluctuation component is extracted using the wavelet decomposition method: CW component = wavelet decomposition(F macro - BL trend ) = [+52.3, +84.7, +43.2, -43.4, -72.1,...]; peak load period identification: PT peak = [8, 9, 10, 11, 17, 18, 19] (corresponding to 8 - 11 am and 5 - 7 pm). Calculate the deviation of the mesoscopic load feature vector from the macroscopic baseline load trend: load fluctuation intensity calculation: LS i ntensity = |F meso [0] - F macroavg / F macromax | = |0.65 - 0.45| = 0.20; load mutation frequency calculation: LM frequency = number of mutations / observation time = 42 / 3600 = 0.0117 times per second. Fit the distribution of the processing delays in each stage of the microscopic processing feature vector: parsing stage delay distribution: DM parse = log - normal distribution (mean μ = 0.223, standard deviation σ = 0.086); mapping stage delay distribution: DM map = normal distribution (μ = 1.68, σ = 0.123); repackaging stage delay distribution: DM pack = normal distribution (μ = 0.92, σ = 0.068). Based on the load fluctuation intensity and load mutation frequency, construct a switching model for high and low load states: load state definition: low load state (L): load level < 150 KB / s; medium load state (M): 150 KB / s ≤ load level < 250 KB / s; high load state (H): load level ≥ 250 KB / s. State transition matrix SM = [[0.75, 0.20, 0.05], [0.15, 0.70, 0.15], [0.10, 0.25, 0.65]], where SM[i, j] represents the probability of transitioning from state i to state j. For example, the probability of transitioning from the low load state to the medium load state is 0.20. Combine the delay probability distribution model with the load state transition matrix: conditional delay distribution model: CDM(t|s) = α s × DMparse + β s × DM map + γ s × DM pack ; where t is the delay value; s is the load status (L, M, or H); α s , β s , γ s are the weight coefficients in status s; weight coefficient matrix: WM = [[0.30, 0.40, 0.30], weight for low load status; [0.35, 0.40, 0.25], weight for medium load status; [0.45, 0.35, 0.20], weight for high load status]. For example, in the high load status, the weight for the parsing stage is 0.45, for the mapping stage is 0.35, and for the repackaging stage is 0.20. Using the hierarchical feature fusion algorithm, integrate all the above features: multi-scale delay feature model MST model is defined as a five-tuple: MST model ={BL trend , CW component , SM, WM, CDM}. This model uses a hierarchical prediction method: use the baseline load trend BL trend and the periodic fluctuation component CW component to predict the macro load level; use the state transition matrix SM to predict the load state transition; use the weight coefficient matrix WM and the conditional delay distribution model CDM to predict the specific delay value.

[0044] Step 2. Protocol conversion delay prediction and compensation strategy generation.

[0045] 2.1. Receive the real-time original communication data set D raw_real , and extract the multi-scale delay features in the current network state: the current macro load level L current = 268.5 KB / s; the current meso load feature F meso_current = [0.72, 0.91, 2.65]; the current micro processing feature F micro_current = [1.45, 1.83, 1.05, 58, 156, 4]. According to the multi-scale delay feature model MST model predict the protocol conversion delay: determine the current load status s = H (high load); obtain the corresponding weight WM[H] = [0.45, 0.35, 0.20]; calculate the expected processing delay E delay = WM[H][0]× F micro_current [0] +WM[H][1] × F micro_current [1] + WM[H][2] × F micro_current[2] = 0.45 × 1.45 + 0.35 × 1.83 + 0.20 × 1.05 = 1.51ms. Predict different types of messages: Expected protocol conversion delay table ET = { "IEC61850_GOOSE-to-DNP3.0": 2.45ms, "IEC61850_MMS-to-DNP3.0": 3.12ms, "IEC61850_GOOSE-to-Modbus": 1.98ms, "Modbus-to-IEC61850": 2.76ms, "DNP3.0-to-IEC61850": 2.83ms}.

[0046] 2.2. Calculate the delay margin based on the expected protocol conversion delay and the end-to-end delay requirements of the message: End-to-end delay requirement table TR = { "Protection trip command": 4ms, "Measurement data": 20ms, "Control command": 10ms, "Status information": 50ms, "Alarm information": 100ms}. Delay margin calculation formula: TM = TR[message type] - ET[protocol conversion type] - OT; where TM is the delay margin and OT is other processing delays (such as network transmission), assuming OT = 1ms. Calculate the delay margin for a "Protection trip command" (IEC61850_GOOSE-to-DNP3.0): TM = 4ms - 2.45ms - 1ms = 0.55ms; Calculate the delay margin for a "Measurement data" (Modbus-to-IEC61850): TM = 20ms - 2.76ms - 1ms = 16.24ms.

[0047] 2.3. Classify messages according to the delay margin and priority marking: Delay margin classification criteria: High sensitivity: TM ≤ 1ms; Medium sensitivity: 1ms < TM ≤ 10ms; Low sensitivity: TM > 10ms. Example message classification: "Protection trip command" (TM = 0.55ms, priority = 7) → High sensitivity; "Control command" (TM = 6.88ms, priority = 5) → Medium sensitivity; "Measurement data" (TM = 16.24ms, priority = 3) → Low sensitivity. For high-sensitivity messages (such as "Protection trip command"), calculate the minimum processing resources required: Minimum CPU resource requirement R cpu = C cpu_base × (ET base / TM target );where C cpu_base is the reference CPU usage rate (40%), ET baseis the reference processing delay (2.45 ms), TM target is the target processing delay (0.55 ms). Calculated R cpu = 40% × (2.45 ms / 0.55 ms) = 178.2%, and two processing cores need to be allocated. The minimum memory requirement R mem = 128 MB (basic processing memory requirement); the minimum bandwidth requirement R bw = 50 Mbps (basic processing bandwidth requirement). Construct the contribution weight matrix of each resource to reducing the conversion delay: Resource - Delay Sensitivity Matrix RTS = { "CPU": 0.65, for every 10% increase in CPU resources, the delay is reduced by 6.5%; "Memory": 0.15, for every 10 MB increase in memory resources, the delay is reduced by 1.5%; "Bandwidth": 0.20, for every 10 Mbps increase in bandwidth resources, the delay is reduced by 2.0%}. Based on the Resource - Delay Sensitivity Matrix, use the resource allocation algorithm to calculate the optimal allocation plan: Allocate for high - sensitivity messages (such as "protection trip instruction"): CPU resource A cpu = 180% (allocate 2 processing cores); memory resource A mem = 192 MB; bandwidth resource A bw = 80 Mbps. Allocate for medium - sensitivity messages (such as "control instruction"): CPU resource A cpu = 90% (allocate 1 processing core); memory resource A mem = 128 MB; bandwidth resource A bw= 50 Mbps. The resource allocation scheme RA = { "High Sensitivity": {CPU: 180%, Memory: 192 MB, Bandwidth: 80 Mbps}, "Medium Sensitivity": {CPU: 90%, Memory: 128 MB, Bandwidth: 50 Mbps}, "Low Sensitivity": {CPU: 50%, Memory: 96 MB, Bandwidth: 30 Mbps}}. According to the allocated resource amount, combined with the protocol type and message complexity of the message, select the most suitable conversion path: The conversion path library CP = { "Full Stack Conversion": {Latency: High, Resource Consumption: High, Integrity: Complete}, "Key Field Conversion": {Latency: Medium, Resource Consumption: Medium, Integrity: Partial}, "Minimum Field Conversion": {Latency: Low, Resource Consumption: Low, Integrity: Minimum}}. Select the "Minimum Field Conversion" path for high-sensitivity messages (such as "Protection Trip Instruction"). Select the "Key Field Conversion" path for medium-sensitivity messages (such as "Control Instruction"). Select the "Full Stack Conversion" path for low-sensitivity messages (such as "Measurement Data"). The conversion path selection = { "High Sensitivity": "Minimum Field Conversion", "Medium Sensitivity": "Key Field Conversion", "Low Sensitivity": "Full Stack Conversion"}. Combining the resource allocation scheme and the conversion path selection, generate a complete latency compensation strategy: The latency compensation strategy TC = { "Resource Allocation": RA, "Conversion Path": CP select , "Processing Priority": { "High Sensitivity": 1, "Medium Sensitivity": 2, "Low Sensitivity": 3}}.

[0048] 2.4. Establish a resource pooling mechanism to avoid resource competition problems when multiple high-priority messages arrive simultaneously: The total resource pool RP total = { "CPU": 400% (4 processing cores), "Memory": 512 MB, "Bandwidth": 200 Mbps}; The reserved resource amount (for high-sensitivity messages) RP reserved = { "CPU": 180% (2 processing cores), "Memory": 192 MB, "Bandwidth": 80 Mbps}; The resource pool configuration RP config = { "Total": RP total , "Reserved": RP reserved , "Available": { "CPU": 220% (2.2 processing cores), "Memory": 320 MB, "Bandwidth": 120 Mbps}}.

[0049] Step 3. Protocol conversion optimization and latency control execution.

[0050] 3.1. Determine the appropriate protocol conversion processing mode for each message according to the conversion path in the delay compensation strategy TC: conversion mode decision TM decision = { "High sensitivity": { "Mode": "Minimum field conversion", "Processing depth": 1, # Only process critical control fields "Priority": 1}, "Medium sensitivity": { "Mode": "Keyword field conversion", "Processing depth": 2, # Process control fields and main status fields "Priority": 2}, "Low sensitivity": { "Mode": "Full stack conversion", "Processing depth": 3, # Process all fields completely "Priority": 3}};

[0051] 3.2. Implement feedforward scheduling according to the resource allocation scheme, and give priority to processing high-delay sensitive services: resource scheduling instruction RD = { "CPU affinity": { "High sensitivity": [0, 1], # Specify to use CPU cores 0 and 1 "Medium sensitivity": [2], # Specify to use CPU core 2 "Low sensitivity": [3] # Specify to use CPU core 3}, "Memory allocation": { "High sensitivity": "192MB", "Medium sensitivity": "128MB", "Low sensitivity": "96MB"}, "Queue priority": { "High sensitivity": 1, # Highest priority queue "Medium sensitivity": 2, # Medium priority queue "Low sensitivity": 3 # Low priority queue}};

[0052] 3.3. Take the IEC 61850 GOOSE protection trip message as an example to analyze its protocol structure: Read the protocol type (IEC61850 GOOSE) and message type (protection trip), query the protocol semantic knowledge base, and extract the complete semantic structure diagram SG full : The complete semantic structure diagram contains the following field groups: message header field group (6 fields); APPID field (1 field); GOOSE control block field group (4 fields); dataset reference field (1 field); timestamp field (1 field); status number field (SqNum, 1 field); test flag field (1 field); configuration version field (1 field); dataset content field group (12 fields); checksum field (1 field). According to the current control requirement (protection trip), identify the necessary function fields FF necessary : Necessary function fields FF necessary= ["APPID", "GOOSE control block identifier", "Timestamp", "Status number", "Trip command type", # Dataset content field 1 "Trip phase information", # Dataset content field 2 "Trip reason code" # Dataset content field 3]. Analyze the application context of the target message in the current business environment (protection trip) and identify the associated status field SF related : Associated status field SF related = ["Test flag", "Configuration version", "Device identifier", # Dataset content field 8 "Protection action time" # Dataset content field 9]. Combine the necessary functional fields and the associated status field to form the key semantic set KS: Key semantic set KS = FF necessary + SF related = ["APPID", "GOOSE control block identifier", "Timestamp", "Status number", "Trip command type", "Trip phase information", "Trip reason code", "Test flag", "Configuration version", "Device identifier", "Protection action time"]. Classify the remaining fields in the complete semantic structure diagram into the non-critical semantic set NKS: Non-critical semantic set NKS = ["Destination MAC address", "Source MAC address", "Ethernet type", "Priority label", "GOOSE PDU length", "GOOSE protocol version", "Dataset reference", "Fault phase current value", # Dataset content field 4 "Fault phase voltage value", # Dataset content field 5 "Zero-sequence current value", # Dataset content field 6 "Zero-sequence voltage value", # Dataset content field 7 "Spare field 1", # Dataset content field 10 "Spare field 2", # Dataset content field 11 "Spare field 3", # Dataset content field 12 "Checksum"]. Assign semantic importance score values SI to each field in the key semantic set: Semantic importance score matrix SI = {"APPID": 0.95, "GOOSE control block identifier": 0.90, "Timestamp": 0.85, "Status number": 0.90, "Trip command type": 1.00, # Highest importance "Trip phase information": 0.98, "Trip reason code": 0.95, "Test flag": 0.85, "Configuration version": 0.80, "Device identifier": 0.75, "Protection action time": 0.88}.

[0053] Read the latency margin of the message (TM = 0.55 ms) and the conversion mode decision (minimum field conversion), and calculate the maximum allowable protocol conversion processing time MT = 0.50 ms. Establish a protocol field processing time model and estimate the time KT required to process all fields in the critical semantic set: Field processing time table FT = { "APPID": 0.05 ms, "GOOSE control block identifier": 0.08 ms, "Timestamp": 0.06 ms, "Status number": 0.04 ms, "Trip command type": 0.08 ms, "Trip phase information": 0.07 ms, "Trip reason code": 0.06 ms, "Test flag": 0.03 ms, "Configuration version": 0.04 ms, "Device identifier": 0.05 ms, "Protection operation time": 0.06 ms}. Critical semantic processing time KT = ∑FT[field] for field in KS = 0.62 ms. Compare the maximum allowable processing time with the critical semantic processing time: MT (0.50 ms) < KT (0.62 ms), the critical semantic set cannot be fully processed and needs to be further trimmed. Construct a performance-semantic trade-off function PST, which maximizes the retained semantic information content under time constraints: Performance-semantic trade-off function PST(F) = ∑(SI[f] × I(f in F)) / ∑FT[f]; where F is the set of fields, SI[f] is the semantic importance score of field f, I(f in F) is the indicator function (1 if f is in F, otherwise 0), and FT[f] is the processing time of field f. Use the performance-semantic trade-off function to select the optimal field subset F opt , such that ∑FT[f] for f in F opt ≤ MT; PST(F opt ) has the maximum value. Through the greedy algorithm, sort the fields by SI[f] / FT[f] and select a subset of the critical semantic set: Optimized critical semantic set KS opt= [ "Trip command type", # SI = 1.00, FT = 0.08ms; "Trip phase information", # SI = 0.98, FT = 0.07ms; "Trip reason code", # SI = 0.95, FT = 0.06ms; "APPID", # SI = 0.95, FT = 0.05ms; "GOOSE control block identifier", # SI = 0.90, FT = 0.08ms; "Status number", # SI = 0.90, FT = 0.04ms; "Timestamp" # SI = 0.85, FT = 0.06ms ]. Total processing time = 0.08 + 0.07 + 0.06 + 0.05 + 0.08 + 0.04 = 0.38ms < MT(0.50ms). Non-critical semantic retention subset NKS kept = [ "Test flag", # SI = 0.85, FT = 0.03ms "Protection operation time" # SI = 0.88, FT = 0.06ms ]. Total processing time = 0.38ms + 0.03ms + 0.06ms = 0.47ms < MT(0.50ms). Integrate and optimize the critical semantic set and non-critical semantic retention subset to form the final semantic pruning scheme SP: Semantic pruning scheme SP = { "Fields to be retained": KS opt , # Optimized critical semantic set; "Secondary fields to be retained": NKS kept , # Non-critical semantic retention subset; "Fields to be supplemented": KS - KS opt + NKS - NKS kept , # Fields that cannot be processed currently; "Processing priority": { "Fields to be retained": 1, "Secondary fields to be retained": 2}, "Estimated total processing time": 0.47ms}.

[0054] Read the source protocol message (IEC 61850 GOOSE protection trip message) and the semantic cropping scheme SP, and prepare the protocol conversion environment and resources. Prioritize the processing of "mandatory reserved fields" (optimized key semantic set), and convert them to the target protocol format (DNP3.0) according to the predefined mapping relationship: The key semantic mapping table KM from IEC 61850 GOOSE to DNP3.0 = { "APPID": "application identifier", "GOOSE control block identifier": "source point code", "status number": "sequence number", "timestamp": "time tag", "trip command type": "BIN output point command code", "trip phase information": "BIN output index number", "trip cause code": "status code"}. The generated key semantic conversion result KR = { "application identifier": "0x4001", "source point code": "P5", "sequence number": "1458", "time tag": "2024-05-09 09:15:23.456", "BIN output point command code": "0x03", "BIN output index number": "0x02", # Trip of phase A "status code": "0x01" # Overcurrent protection}. Process the "secondary reserved fields" (non-critical semantic reserved subset), and convert them to the target protocol format: The secondary semantic mapping table SM from IEC 61850 GOOSE to DNP3.0 = { "test flag": "test bit", "protection action time": "event time"}; The generated secondary semantic conversion result SR = { "test bit": "0", "event time": "100ms"}. Mark the fields that could not be processed in the current conversion cycle with a to-be-supplemented identifier, record their original information and target mapping relationship, and output to the to-be-supplemented data cache PS: To-be-supplemented data cache PS = { "message ID": "PKT-001254", "to-be-supplemented fields": [ { "original field": "configuration version", "target field": "configuration version", "original value": "2", "mapping relationship ID": "M17"}, { "original field": "device identifier", "target field": "device identification", "original value": "PROT1", "mapping relationship ID": "M23"}, { "original field": "destination MAC address", "target field": "none", "original value": "01:0C:CD:01:00:01", "mapping relationship ID": "none"}, #... Other unprocessed fields ]}.Assemble the final target protocol message structure, fill in the converted semantic content, and form the optimized conversion result OR: DNP3.0 message structure = { "Message Header": { "Start Byte": "0x0564", "Length": "18", "Control Code": "0x44", "Destination Station Address": "3", "Source Station Address": "1"}, "Application Layer": { "Application Control": "0xC0", # Acknowledge Request "Function Code": "0x03", # Direct Operation "Internal Indication": "0x00", "Application Identifier": KR["Application Identifier"], "Source Point Code": KR["Source Point Code"], "Sequence Number": KR["Sequence Number"], "Time Tag": KR["Time Tag"], "Object Header": { "Group Number": "0x0C", # BIN Output "Variation Point": "0x01", # Single Point "Qualifier": "0x17", # Number of Fields within Range 7 "BIN Output Point Command Code": KR["BIN Output Point Command Code"], "BIN Output Index Number": KR["BIN Output Index Number"], "Status Code": KR["Status Code"], "Test Bit": SR["Test Bit"], "Event Time": SR["Event Time"]}}, "Checksum": "0xA2B6"}.

[0055] Read the real-time processing delay RT of the current protocol conversion process, which is 0.52ms. Calculate the deviation from the expected protocol conversion delay (ET = 0.47ms) to obtain the delay deviation value DV = RT - ET = 0.05ms. Set the delay deviation threshold DT = 0.1ms. When |DV| > DT, trigger the feedback adjustment process. In this example, |DV| (0.05ms) < DT (0.1ms), so there is no need to trigger the feedback adjustment. However, for the purpose of demonstrating the feedback adjustment process, assume that in a subsequent message processing, RT = 0.65ms and ET = 0.47ms are measured, and DV = 0.18ms > DT is calculated, which requires triggering the feedback adjustment. Analyze the delay deviation value DV = 0.18ms > 0, and determine that the current delay situation is "delay exceeding expectations". Quickly adjust the semantic pruning scheme, further streamline the non-critical semantic retention subset, and form the emergency pruning scheme ESP: Remove "protection action time" from the non-critical semantic retention subset NKS kept to save 0.06ms of processing time: Emergency Pruning Scheme ESP = { "Fields to be Retained": KS opt , # Unchanged "Secondary Retained Fields": ["Test Flag"], # Only retain the test flag "Fields to be Supplemented": KS - KS opt+ NKS - ["Test Flag"], # More fields to be supplemented "Processing Priority": { "Required Retained Fields": 1, "Secondary Retained Fields": 2}, "Estimated Total Processing Time": 0.41ms}. Apply for additional emergency processing resources and update the resource allocation plan to the emergency resource plan ERP: Emergency Resource Plan ERP = { "CPU": 220%, # Increased to 2.2 cores "Memory": 192MB, # Remains unchanged "Bandwidth": 100Mbps # Increased by 20%}. For resource redundancy situations, expand the non-critical semantic retention subset and release excess resources; in this case, since the delay exceeded expectations, it is not executed. According to the actual adjustment results, update the parameters of the delay prediction model to improve future prediction accuracy: Model Adjustment Parameters MAP = { "Adjustment of Processing Delay Coefficient": 1.15, # The actual processing delay is approximately 15% higher than predicted "Adjustment of State Transition Probability": [0, 0, 0.05], # The probability of the high-load state persisting increases by 5% "Adjustment of Weight Coefficient Matrix": [[0, 0, 0], [0, 0, 0], [0.05, -0.03, -0.02]] # The weight in the parsing stage increases by 5% in the high-load state}. The updated weight coefficient matrix is: WM updated = [ [0.30, 0.40, 0.30], # The weights in the low-load state remain unchanged; [0.35, 0.40, 0.25], # The weights in the medium-load state remain unchanged; [0.50, 0.32, 0.18] # The weights in the high-load state are adjusted ].

[0056] Read the non-keyword field information and related metadata in the pending supplementary data cache PS, and evaluate the current network load status: The current network load CL = 196.4 KB / s (medium load). Based on the network load status and the semantic importance of the pending supplementary data, calculate the optimal supplementary transmission time window ST: Priority sorting of the pending supplementary data: "Configuration version" (SI = 0.80); "Device identifier" (SI = 0.75); "Other non-keyword fields" (SI < 0.50). The network load prediction indicates that a low-load period will start after 12 seconds and last for about 30 seconds. Supplementary transmission time window ST = [09:15:35.500, 09:16:05.500]. Construct a dedicated supplementary data packet structure SD, which contains metadata such as the original message identifier, timestamp, and supplementary content type: Supplementary data packet SD = { "Packet type": "0xF2", # Supplementary data type "Original message ID": "PKT-001254", "Original message timestamp": "2024-05-09 09:15:23.456", "Supplementary timestamp": "2024-05-09 09:15:35.500", "Supplementary content type": "0x01", # Non-critical semantic supplement "Number of supplementary fields": 15, "Supplementary content": [ {"Field ID": "0x17", "Field name": "Configuration version", "Field value": "2"}, {"Field ID": "0x23", "Field name": "Device identifier", "Field value": "PROT1"}, #... Other supplementary fields ], "Checksum": "0xB7C9"}. Within the determined supplementary transmission time window, use a low-priority channel to transmit the supplementary data packet to ensure that it does not interfere with the current critical business flow: Supplementary data transmission configuration STC = { "Transmission channel": "Channel 4", # Low-priority channel "QoS level": "Best effort", "Transmission time": "2024-05-09 09:15:40.000", # Specific time selected within the time window "Timeout setting": "5 seconds", "Number of retries": 2}. At the target device end, receive the supplementary data packet and associate it with the corresponding original conversion message through the message identifier in it: Message association result MA = { "Original message ID": "PKT-001254", "Original message storage location": "0x12A8F4", "Original message processing status": "Processed", "Original message execution result": "Trip successful"}.Merge the original conversion message and supplementary data content, reconstruct the complete protocol message semantics, and output the complete conversion data CD: Complete conversion data CD = Optimized conversion result OR + { "Application layer": { "Extended fields": { "Configuration version": "2", "Device identifier": "PROT1", #... other supplementary fields}}}.

[0057] Step 4: End-to-end delay awareness and topology reconstruction decision.

[0058] 4.1. Based on the multi-scale delay feature model MST model and real-time processing delay RT data, identify the delay bottleneck points and congestion areas in the current network topology: There are 16 nodes and 24 links in the network topology. By analyzing the processing delay data for nearly 1 hour, calculate the bottleneck metrics for each node and link: Node bottleneck degree index NBI calculation formula: NBI = (P avg / P max ) × (Q avg / Q max ) × (D avg / D threshold ); where P avg is the average processing load, P max is the maximum processing capacity, Q avg is the average queue length, Q max is the maximum queue length, D avg is the average processing delay, D threshold is the delay threshold. Link congestion degree index LCI calculation formula: LCI = (B avg / B max ) × (D var / D varmax ); where B avg is the average bandwidth occupancy, B max is the maximum bandwidth, D var is the delay change rate, D varmax is the maximum acceptable delay change rate.

[0059] Node bottleneck analysis results: Node 6 (Protocol Conversion Gateway 1): NBI = 0.85, congestion duration = 42 minutes / hour; Node 9 (Protocol Conversion Gateway 2): NBI = 0.72, congestion duration = 28 minutes / hour; Node 12 (Network Switch 3): NBI = 0.68, congestion duration = 25 minutes / hour; Other nodes: NBI < 0.50. Link congestion analysis results: Link 8-6 (Protection Device 2 to Gateway 1): LCI = 0.78, congestion duration = 35 minutes / hour; Link 5-12 (Protection Device 4 to Switch 3): LCI = 0.65, congestion duration = 23 minutes / hour; Other links: LCI < 0.60. Network Bottleneck Analysis Report NBR = { "Node bottleneck": [ {"Node ID": 6, "Node type": "Protocol Conversion Gateway 1", "NBI": 0.85, "Congestion duration": 42}, {"Node ID": 9, "Node type": "Protocol Conversion Gateway 2", "NBI": 0.72, "Congestion duration": 28}, {"Node ID": 12, "Node type": "Network Switch 3", "NBI": 0.68, "Congestion duration": 25} ], "Link congestion": [ {"Link ID": "8-6", "Link type": "Protection Device 2 to Gateway 1", "LCI": 0.78, "Congestion duration": 35}, {"Link ID": "5-12", "Link type": "Protection Device 4 to Switch 3", "LCI": 0.65, "Congestion duration": 23} ], "Bottleneck cause analysis": { "Node 6": "Handling multiple protocol conversion tasks, serious resource competition", "Link 8-6": "Shared channel for protection trip commands and measurement data, bandwidth contention"}}.

[0060] 4.2. Extract the bottleneck degree index and congestion duration of each node and link from the network bottleneck analysis report NBR: The bottleneck degree index matrix BIM = [[6, 0.85, 42], # [Node ID, NBI, Congestion duration][9, 0.72, 28], [12, 0.68, 25], ["8-6", 0.78, 35], # [Link ID, LCI, Congestion duration]["5-12", 0.65, 23]]. Analyze the end-to-end delay requirements of various service flows in the substation, and determine the delay tolerance and service importance weight of each type of service: The service delay requirement matrix BDM = [["Protection trip instruction", 4, 1.0], # [Service type, Delay tolerance (ms), Importance weight]["Measurement data", 20, 0.6], ["Control instruction", 10, 0.8], ["Status information", 50, 0.5], ["Alarm information", 100, 0.7]]. Construct an initial performance evaluation function and calculate the delay improvement potential score of each bottleneck point: The formula for calculating the delay improvement potential score IPS: IPS = (BIM[i][1] × BIM[i][2]) / C[i]; where BIM[i][1] is the bottleneck degree index, BIM[i][2] is the congestion duration, and C[i] is the transformation cost coefficient (assuming the node transformation cost is 2.0 and the link transformation cost is 1.0). Calculate the node improvement potential score: Node 6: IPS = (0.85 × 42) / 2.0 = 17.85; Node 9: IPS = (0.72 × 28) / 2.0 = 10.08; Node 12: IPS = (0.68 × 25) / 2.0 = 8.50. Calculate the link improvement potential score: Link 8-6: IPS = (0.78 × 35) / 1.0 = 27.30; Link 5-12: IPS = (0.65 × 23) / 1.0 = 14.95. The node improvement potential score matrix IPSM = [[6, 17.85], [9, 10.08], [12, 8.50], ["8-6", 27.30], ["5-12", 14.95]]. Construct a network traffic distribution model to simulate the impact of different topology changes on the delay of each service flow: Topology change types: Add nodes (new protocol conversion gateways); Modify links (add dedicated links); Load diversion (service separation); Protocol conversion point relocation.For each type of topology change, calculate the traffic flow delay impact factor TIF: Topology Impact Mapping Matrix TIM = [Topology change type, Protection trip delay impact, Measurement data delay impact, Control instruction delay impact, Status information delay impact, Alarm information delay impact] = [1, -0.65, -0.30, -0.45, -0.25, -0.20], # Add node [2, -0.75, -0.50, -0.55, -0.35, -0.25], # Modify link [3, -0.60, -0.70, -0.50, -0.60, -0.65], # Load diversion [4, -0.80, -0.40, -0.60, -0.30, -0.25] # Protocol conversion point relocation]. Among them, negative values represent the proportion of delay reduction. For example, the impact factor of adding a node on the protection trip instruction delay is -0.65, indicating that the delay can be reduced by 65%. Integrate the Node Improvement Potential Score Matrix IPSM and the Topology Impact Mapping Matrix TIM to construct the comprehensive network optimization objective function NOF: Network Optimization Objective Function NOF(T, N) = ∑(BDM[j][2] × min(TIM[T][j + 1] × (-1) × 100, BDM[j][1])) × ∑IPSM[i][1]; where T is the topology change type, N is the set of changed nodes / links, BDM[j][2] is the importance weight of service j, TIM[T][j + 1] is the delay impact factor of topology change T on service j, BDM[j][1] is the delay tolerance of service j, and IPSM[i][1] is the improvement potential score of node / link i. This function maximizes the delay performance gain under constraints such as resource limitation (at most 3 points can be modified), reliability requirement (redundancy is not less than 2), and service continuity (services are not interrupted during the modification process).

[0061] 4.3. Generate a series of potential topology adjustment plans based on the existing network topology and the network optimization objective function NOF: Candidate Plan Pool CP = { "Plan 1": { "Type": 1, # Add node "Change Point": [{"Newly Added": "Protocol Conversion Gateway 3", "Location": "Near Protection Device 2", "Function": "Dedicated Protection Service Protocol Conversion"}], "Initial NOF Estimate": 245.6}, "Plan 2": { "Type": 2, # Modify link "Change Point": [{"Added": "High-Speed Dedicated Link", "Start Point": "Protection Device 2", "End Point": "Gateway 1", "Bandwidth": "1Gbps"}], "Initial NOF Estimate": 273.8}, "Plan 3": { "Type": 3, # Load shunting "Change Point": [{"Adjusted": "Service Separation", "Protection Service": "Gateway 1", "Non-Protection Service": "Gateway 2"}], "Initial NOF Estimate": 216.3}, "Plan 4": { "Type": 4, # Relocate protocol conversion point "Change Point": [{"Moved": "Gateway 1", "New Location": "Near Switch 1", "Optimization Objective": "Reduce Transmission Distance"}], "Initial NOF Estimate": 198.7}, "Plan 5": { "Type": [1, 2], # Hybrid plan: add node + modify link "Change Point": [ {"Newly Added": "Protocol Conversion Gateway 3", "Location": "Near Protection Device 2", "Function": "Dedicated Protection Service Protocol Conversion"}, {"Added": "High-Speed Dedicated Link", "Start Point": "Protection Device 4", "End Point": "Switch 3", "Bandwidth": "1Gbps"} ], "Initial NOF Estimate": 312.5}}. For each plan in the candidate plan pool, refine the specific implementation steps: Take "Plan 5" as an example to refine its implementation steps: Link Adjustment Details LD = { "Step 1": "Install the new Protocol Conversion Gateway 3 in Cabinet 3", "Step 2": "Configure the IP address of Gateway 3 as 10.1.1.15", "Step 3": "Configure Gateway 3 to support the dedicated conversion function from IEC61850 to DNP3.0", "Step 4": "Deploy the semantic dynamic pruning module on Gateway 3", "Step 5": "Lay the direct-connect optical fiber from Protection Device 2 to Gateway 3", "Step 6": "Lay the gigabit optical fiber from Protection Device 4 to Switch 3", "Step 7": "Update the routing table to forward the trip command of Protection Device 2 to Gateway 3", "Step 8": "Update the routing table to forward the high-priority messages of Protection Device 4 through the new link"}.

[0062] The traffic routing rule FR = { "Rule 1": "The protection trip command is sent after being converted by gateway 3 from protection device 2", "Rule 2": "The measurement data is transmitted along the original path", "Rule 3": "The control command divides the path according to the priority", "Rule 4": "All messages of protection device 4 are transmitted through the newly added high-speed link"}. The conversion node configuration CC = { "Gateway 1 configuration": { "Mainly responsible for": "Converting control commands and measurement data", "CPU allocation": "70%", "Protocol support": ["IEC61850-MMS to DNP3.0", "Modbus to IEC61850"]}, "Gateway 2 configuration": { "Mainly responsible for": "Converting status information and alarm information", "CPU allocation": "60%", "Protocol support": ["IEC61850 to Modbus", "DNP3.0 to IEC61850"]}, "Gateway 3 configuration": { "Mainly responsible for": "Special conversion of protection trip commands", "CPU allocation": "90% dedicated to protection services", "Protocol support": ["IEC61850-GOOSE to DNP3.0"]}}. The topology adjustment plan TA = { "Plan ID": 5, "Link adjustment details": LD, "Traffic routing rule": FR, "Conversion node configuration": CC, "Expected effect": "The delay of the protection trip command is reduced by 80%, and the average delay of other services is reduced by 40%"}.

[0063] Preliminarily screen each topology adjustment plan and eliminate unreasonable or overly difficult-to-implement plans: The plan screening criteria SS = { "feasibility threshold": 0.7, # between 0 and 1, the higher the more stringent "cost ceiling": 50,000, # unit: yuan "upper limit of implementation difficulty": 0.8, # between 0 and 1, the higher the more difficult "upper limit of business interruption risk": 0.2 # between 0 and 1, the higher the greater the risk}. Evaluate all plans: Plan 1: feasibility = 0.85, cost = 30,000, implementation difficulty = 0.6, business interruption risk = 0.15; Plan 2: feasibility = 0.90, cost = 15,000, implementation difficulty = 0.5, business interruption risk = 0.20; Plan 3: feasibility = 0.75, cost = 5,000, implementation difficulty = 0.4, business interruption risk = 0.10; Plan 4: feasibility = 0.65, cost = 25,000, implementation difficulty = 0.9, business interruption risk = 0.30; Plan 5: feasibility = 0.80, cost = 45,000, implementation difficulty = 0.7, business interruption risk = 0.18. Eliminate Plan 4 (feasibility is lower than the threshold, implementation difficulty is higher than the upper limit, and business interruption risk is higher than the upper limit). The candidate topology plan set CTS = {Plan 1, Plan 2, Plan 3, Plan 5}.

[0064] 4.4. Build a detailed network simulation model to accurately reflect the topological structure, device characteristics, and business flow characteristics of the current substation network: The network simulation model includes the following components: Topological structure model: The connection relationship of 16 nodes and 24 links; Device characteristics model: Parameters such as the processing capacity, queue length, and buffer size of each device; Protocol characteristics model: The message structures and processing characteristics of IEC61850, DNP3.0, and Modbus; Business flow model: The generation frequency, data volume, and priority of 5 types of business flows; Delay calculation model: The calculation methods of transmission delay, queuing delay, and processing delay. For each plan in the candidate topology plan set CTS, use the simulation model for detailed evaluation: Simulation condition settings: Simulation duration: 3600 seconds (1 hour); Load mode: [low load (20 minutes) → medium load (20 minutes) → high load (20 minutes)]; Business occurrence mode: Generated according to the actual substation business statistics distribution; Key event: Trigger 2 protection trip commands during high load.

[0065] Simulation Results (Partial): Simulation Results of Scheme 1: Average Delay of Protection Tripping Command: 1.25 ms (Original: 3.85 ms), a reduction of 67.5%; Average Delay of Measurement Data: 12.6 ms (Original: 15.8 ms), a reduction of 20.3%; Average Delay of Control Command: 5.8 ms (Original: 8.5 ms), a reduction of 31.8%; Average Delay of Status Information: 38.5 ms (Original: 45.2 ms), a reduction of 14.8%; Average Delay of Alarm Information: 85.2 ms (Original: 96.3 ms), a reduction of 11.5%; Network Congestion Probability under High Load Conditions: 0.35 (Original: 0.72), a reduction of 51.4%. Simulation Results of Scheme 2: Average Delay of Protection Tripping Command: 0.95 ms (Original: 3.85 ms), a reduction of 75.3%; Average Delay of Measurement Data: 10.2 ms (Original: 15.8 ms), a reduction of 35.4%; Average Delay of Control Command: 6.1 ms (Original: 8.5 ms), a reduction of 28.2%; Average Delay of Status Information: 40.1 ms (Original: 45.2 ms), a reduction of 11.3%; Average Delay of Alarm Information: 88.5 ms (Original: 96.3 ms), a reduction of 8.1%; Network Congestion Probability under High Load Conditions: 0.40 (Original: 0.72), a reduction of 44.4%. Simulation Results of Scheme 3: Average Delay of Protection Tripping Command: 1.85 ms (Original: 3.85 ms), a reduction of 51.9%; Average Delay of Measurement Data: 8.5 ms (Original: 15.8 ms), a reduction of 46.2%; Average Delay of Control Command: 6.8 ms (Original: 8.5 ms), a reduction of 20.0%; Average Delay of Status Information: 30.2 ms (Original: 45.2 ms), a reduction of 33.2%; Average Delay of Alarm Information: 65.4 ms (Original: 96.3 ms), a reduction of 32.1%; Network Congestion Probability under High Load Conditions: 0.28 (Original: 0.72), a reduction of 61.1%. Simulation Results of Scheme 5: Average Delay of Protection Tripping Command: 0.75 ms (Original: 3.85 ms), a reduction of 80.5%; Average Delay of Measurement Data: 9.2 ms (Original: 15.8 ms), a reduction of 41.8%; Average Delay of Control Command: 5.2 ms (Original: 8.5 ms), a reduction of 38.8%; Average Delay of Status Information: 35.1 ms (Original: 45.2 ms), a reduction of 22.3%; Average Delay of Alarm Information: 70.5 ms (Original: 96.3 ms), a reduction of 26.8%; Network Congestion Probability under High Load Conditions: 0.22 (Original: 0.72), a reduction of 69.4%.The expected end-to-end delay ET = { "Solution 1": [1.25, 12.6, 5.8, 38.5, 85.2], "Solution 2": [0.95, 10.2, 6.1, 40.1, 88.5], "Solution 3": [1.85, 8.5, 6.8, 30.2, 65.4], "Solution 5": [0.75, 9.2, 5.2, 35.1, 70.5]}.

[0066] Introduce two additional metrics: reliability score and implementation complexity score. Calculation basis for reliability score: System redundancy (the higher the better): the redundancy degree of the critical links provided by the solution; Single-point failure recovery ability (the higher the better): the recovery speed of the system for a single node or link failure; Security isolation (the higher the better): the isolation degree between critical services and non-critical services. Calculation basis for implementation complexity score: Amount of hardware change (the less the better): the number of devices that need to be added or replaced; Software configuration complexity (the lower the better): the number of software and configurations that need to be updated; Service interruption time (the shorter the better): the duration of service interruption during implementation; Professional skill requirement (the lower the better): the professional skill level required for implementers. Scoring results (out of 10): Reliability score RS = { "Solution 1": 8.2, "Solution 2": 7.5, "Solution 3": 6.8, "Solution 5": 8.8}; Implementation complexity score CS (the lower the better) = { "Solution 1": 6.5, "Solution 2": 4.2, "Solution 3": 3.0, "Solution 5": 7.8}.

[0067] Apply the multi-objective optimization method for comprehensive evaluation: Multi-objective optimization weight setting: Delay performance weight WT = 0.6; Reliability weight WR = 0.3; Implementation complexity weight WC = 0.1 (complexity is a negative metric, take the inverse value). Formula for delay performance score TS: TS = ∑(BDM[j][2]× (ET orig [j] - ET[i][j]) / ET orig [j]); where BDM[j][2] is the importance weight of service j, ET orig[j] is the original time delay, and ET[i][j] is the expected time delay of Scheme i. The calculation of the time delay performance score (normalized to a 10-point scale): TS["Scheme 1"] = (1.0×67.5% + 0.6×20.3% + 0.8×31.8%+ 0.5×14.8% + 0.7×11.5%) / (1.0+0.6+0.8+0.5+0.7) × 10 = 7.2 TS["Scheme 2"] =(1.0×75.3% + 0.6×35.4% + 0.8×28.2% + 0.5×11.3% + 0.7×8.1%) / (1.0+0.6+0.8+0.5+0.7) × 10 = 7.8 TS["Scheme 3"]= (1.0×51.9% + 0.6×46.2% + 0.8×20.0% +0.5×33.2% + 0.7×32.1%) / (1.0+0.6+0.8+0.5+0.7) × 10 = 6.9 TS["Scheme 5"]=(1.0×80.5% + 0.6×41.8% + 0.8×38.8% + 0.5×22.3% + 0.7×26.8%) / (1.0+0.6+0.8+0.5+0.7) × 10 = 9.2. The calculation formula for the comprehensive optimization score COS: COS = WT × TS + WR × RS +WC × (10 - CS); The calculation of the comprehensive optimization score: COS["Scheme 1"]= 0.6 × 7.2 + 0.3 × 8.2 + 0.1× (10 - 6.5) = 7.07 COS["Scheme 2"]= 0.6 × 7.8 + 0.3 × 7.5 + 0.1 × (10 -4.2) = 7.49 COS["Scheme 3"]= 0.6 × 6.9 + 0.3 × 6.8 + 0.1 × (10 - 3.0) = 6.92COS["Scheme 5"]= 0.6 × 9.2 + 0.3 × 8.8 + 0.1 × (10 - 7.8) = 8.68. Select the scheme with the highest comprehensive optimization score as the optimal topology reconstruction scheme: The ranking of the comprehensive optimization scores: Scheme 5: 8.68 points; Scheme 2: 7.49 points; Scheme 1: 7.07 points; Scheme 3: 6.92 points. The optimal topology reconstruction scheme ORP = Scheme 5, that is, the hybrid scheme (adding a protocol conversion gateway + modifying the link).Solution evaluation result ER = {"Best solution": "Solution 5", "Overall score": 8.68, "Delay improvement": "Protection tripping delay is reduced by 80.5%, and average delay is reduced by 42.0%", "Reliability score": 8.8, "Implementation complexity": 7.8, "Expected return on investment": 3.5 # Return on investment = performance improvement percentage / cost}.

[0068] 4.5. Based on the optimal topology reconstruction scheme ORP (Scheme 5), perform adaptive reconstruction of the network topology: Reconstruction execution steps: install a new protocol conversion gateway 3 in cabinet 3, configure the IP address to 10.1.1.15; deploy the protocol semantics dynamic tailoring module of the present invention on gateway 3; lay a direct optical fiber from protection device 2 to gateway 3; lay a gigabit optical fiber from protection device 4 to switch 3; configure gateway 3 to support the dedicated conversion function from IEC61850-GOOSE to DNP3.0; update the routing table to forward the tripping instruction of protection device 2 to gateway 3; update the routing table to forward the high priority message of protection device 4 through the new link; reallocate the responsibilities of the protocol conversion processing nodes, gateway 1 is responsible for the conversion of control instructions and measurement data, gateway 2 is responsible for the conversion of status information and alarm information, and gateway 3 focuses on the conversion of protection tripping instructions. Reconstruction execution result RE = { "Execution status": "Completed", "Actual execution time": "2024-05-10 02:00:00 to 04:30:00", "Service interruption time": "15 minutes", "Verification test result": { "Actual delay of protection tripping command": 0.78ms, "Delay before reconstruction": 3.85ms, "Improvement ratio": "79.7%", "Safety margin": 3.22ms, "Verification conclusion": "In line with design expectations"}}.

[0069] To verify the effectiveness of this embodiment, actual tests were conducted on the key business scenarios in the secondary system of the substation. The tests were carried out in the actual 220 kV substation environment to compare the performance differences between this embodiment and the traditional protocol conversion method. In the scenario of protection trip commands: By simulating the overcurrent protection action, triggering the conversion of protection trip commands from IEC 61850 GOOSE to DNP3.0, and statistically analyzing the latency data of 100 operations: The average conversion latency of the traditional method is 3.85 ms, the maximum conversion latency is 9.65 ms, the minimum conversion latency is 2.12 ms, the latency standard deviation is 1.85 ms, and the proportion of exceeding the latency requirement (4 ms) is 38%; The average conversion latency of this embodiment is 0.78 ms, the maximum conversion latency is 1.25 ms, the minimum conversion latency is 0.65 ms, the latency standard deviation is 0.15 ms, and the proportion of exceeding the latency requirement (4 ms) is 0%. The average latency is reduced by 79.7%, the latency fluctuation is reduced by 91.9%, the safety margin is increased by 3.22 ms, the reliability is improved, and all commands are completed within the required latency. In the multi-service concurrent scenario test, simulating the multi-service concurrent scenario under high load conditions in the substation, and testing the overall performance before and after the network topology reconstruction: Before the topology reconstruction, the average network load rate is 78.5%, the peak load rate is 92.3%, the CPU utilization rate of the key node is 85.6%, the bandwidth utilization rate of the key link is 87.2%, and the network congestion probability is 0.72; After the topology reconstruction: The average network load rate is 52.3%, the peak load rate is 68.5%, the CPU utilization rate of the key node is 60.2%, the bandwidth utilization rate of the key link is 55.4%, and the network congestion probability is 0.22. The network load balance is improved by 33.4%, the utilization rate of key resources is decreased by 29.7%, the congestion probability is reduced by 69.4%, and the overall network performance is improved by 42.8%.

[0070] Testing the optimization effect of the protocol semantic dynamic pruning technology on the conversion latency under different load conditions: Under low load conditions (network load < 30%), the latency of the traditional method (full conversion) is 2.25 ms; The latency of this embodiment (dynamic pruning) is 1.35 ms; The improvement ratio is 40.0%; The semantic retention rate is 92.5%. Under medium load conditions (network load 30% - 70%), the latency of the traditional method (full conversion) is 3.45 ms; The latency of this embodiment (dynamic pruning) is 1.65 ms; The improvement ratio is 52.2%; The semantic retention rate is 85.3%. Under high load conditions (network load > 70%), the latency of the traditional method (full conversion) is 5.85 ms; The latency of the traditional method (simplified conversion) is 1.95 ms, and the semantic retention rate is 45.0%; The latency of this embodiment (dynamic pruning) is 0.78 ms; The improvement ratio compared with full conversion is 86.7%; The improvement ratio compared with simplified conversion is 60.0%; The key semantic retention rate is 100%; The overall semantic retention rate is 76.2%.

[0071] The system of this embodiment was subjected to a 30 - day continuous stability test: for the traditional method (30 - day statistics), the number of protocol conversion failures was 12, the number of protocol conversion timeouts was 105, the number of network congestion events was 42, and the number of system automatic restarts was 3; for this embodiment (30 - day statistics), the number of protocol conversion failures was 0, the number of protocol conversion timeouts was 2, the number of network congestion events was 5, and the number of system automatic restarts was 0. In comparison, the conversion reliability was increased by 100%; the timeout events were reduced by 98.1%; the congestion events were reduced by 88.1%; and the system stability was increased by 100%.

[0072] This embodiment details the specific implementation process of the adaptive topology reconstruction method for the secondary communication network of a substation based on delay sensitivity analysis. Through test verification in the actual 220kV substation environment, this embodiment has the following outstanding advantages: The multi - scale delay feature fusion model realizes high - precision prediction of protocol conversion delay and reduces the prediction error. The protocol semantic dynamic pruning technology breaks the traditional "all - or - nothing" processing mode, dynamically adjusts the semantic retention level according to delay sensitivity, and ensures that the protocol conversion delay of key protection services is stably controlled within 1 millisecond. The end - to - end delay - aware topology reconstruction decision considers the deployment of protocol conversion nodes and the optimization of network traffic distribution, and realizes the collaborative optimization of protocol conversion, resource allocation, and network topology. The method based on the performance - semantics trade - off function optimizes the processing delay to the greatest extent while ensuring the functional correctness, and at the same time ensures the ultimate data integrity through the asynchronous supplementary transmission mechanism. The feedback adjustment mechanism constructs a complete closed - loop control system, which can respond to network load fluctuations in real time and ensure the real - time guarantee of key services. Through this embodiment, when the secondary communication network of a substation faces the problem of protocol conversion delay uncertainty in a multi - protocol environment, it shows significant performance improvement, not only improving the system reliability and stability, but also providing an important guarantee for the safe and efficient operation of the smart grid.

[0073] The present invention integrates the delay characteristics at three levels: macroscopic load trends, mesoscopic emergencies, and microscopic processing details, and establishes a prediction model that can accurately capture the delay fluctuation law in the substation multi-protocol network. By decomposing the waveform to separate the periodic load from the baseline load and combining with conditional delay distribution modeling, the delay prediction error is reduced. In the secondary system of the substation, it provides millisecond-level delay guarantee for key services such as protection tripping, fundamentally solving the problem of highly uncertain protocol conversion delay in the prior art. By precisely quantifying the contribution degrees of different resources (processor, memory, bandwidth) to delay improvement, the optimal allocation of resources is achieved. By classifying messages into three levels of sensitivity: high, medium, and low, and pre-allocating resources for high-sensitivity messages, important protection signals and control instructions can be given priority in processing. In the scenario of substation emergency handling, this strategy stabilizes the protocol conversion delay of key instructions such as overcurrent protection tripping within 0.8 milliseconds, showing a significant improvement compared with traditional methods. Through the resource pooling mechanism, the resource competition problem when multiple high-priority messages arrive simultaneously is effectively avoided, ensuring the stability and reliability of the substation protection system under network load fluctuations, thereby preventing protection action delays caused by communication delays. The protocol semantic dynamic pruning technology breaks through the "all-or-nothing" processing mode in traditional protocol conversion. By identifying the key semantic set and non-key semantic set in the message and using the performance-semantic trade-off function to dynamically adjust the semantic retention level. By distinguishing necessary functional fields and associated status fields, it can ensure the correct execution of the core functions of control commands first when the delay budget is tight. Especially in the case of network congestion, the system can intelligently prune non-key information to ensure the timely transmission of emergency protection instructions, effectively preventing protection failures or misoperations caused by protocol conversion delays, and improving the security and stability of the substation secondary system. By real-time monitoring the processing delay during protocol conversion, when a significant deviation from the expected delay is detected, the resource allocation and semantic pruning levels can be dynamically adjusted. By constructing a delay deviation threshold judgment and two-way adjustment strategy, it can not only handle emergency situations where the delay exceeds expectations but also deal with optimization opportunities for resource redundancy. Keeping the delay recovery within a safe range enables the system to adaptively learn and optimize, and the delay prediction accuracy increases with the increase of running time, forming a true adaptive control closed-loop, effectively overcoming the uncertainty brought by the complex and changeable environment of the substation. It realizes network optimization for end-to-end delay. A network bottleneck analysis and topology impact mapping matrix are established, which can accurately evaluate the impact of different topology adjustments on various service flows. Especially for data flows spanning multiple protocol regions, the system can intelligently optimize the deployment location and quantity of protocol conversion nodes, reducing the additional delay introduced by protocol conversion, ensuring that even in a multi-protocol hybrid environment, the end-to-end delay of the substation secondary system can meet the strict requirements of the IEC 61850 standard for time-critical messages, and improving the reliability and security of the power system.

[0074] The preferred embodiments of the present invention have been described in detail above. However, the present invention is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all fall within the protection scope of the present invention.

Claims

1. A method for adaptive topology reconfiguration of the communication network in the secondary system of a substation, characterized in that Including: Collect the communication data of multi-protocol networks in the substation secondary system, extract multi-scale delay sensitivity features, and construct a multi-scale delay feature model; Use the multi-scale delay feature model to predict the protocol conversion delay and generate a delay compensation strategy for delay-sensitive services; Execute protocol conversion optimization and delay control according to the delay compensation strategy, obtain the optimized conversion result and real-time processing delay, and conduct end-to-end delay perception analysis in combination with the multi-scale delay feature model to generate and execute the optimal topology reconstruction scheme.

2. The method according to claim 1, characterized in that, Construct a multi-scale delay feature model, including: Collect the communication data of multi-protocol networks in the substation secondary system, including the packet timestamps, payload sizes, priority tags, and network device status information of different protocols, and generate an original communication data set; Based on the original communication data set, sequentially extract macroscopic, mesoscopic, and microscopic delay features to obtain macroscopic and mesoscopic load feature vectors, and microscopic processing feature vectors, and construct a multi-scale delay feature model accordingly.

3. The method according to claim 2, wherein Construct a multi-scale delay feature model, including: Extract the baseline load trend and periodic fluctuation components from the macroscopic load feature vector; Read the mesoscopic load feature vector, calculate its deviation from the baseline load trend, and obtain the load fluctuation intensity and load mutation frequency indicators; and construct a switching model for high and low load states based on this to form a load state transition matrix; Based on the microscopic processing feature vector, perform distribution fitting to obtain the delay probability distribution model for each processing stage and combine it with the load state transition matrix to construct a conditional delay distribution model considering state transition; Integrate the baseline load trend, periodic fluctuation components, and conditional delay distribution model into a multi-scale delay feature model.

4. The method according to claim 1, wherein Generate a delay compensation strategy for delay-sensitive services, including: Receive communication data, extract the multi-scale delay features in the current network state and input them into the multi-scale delay feature model to obtain the expected protocol conversion delay of different types of messages under the current network conditions; Calculate the delay margin based on the expected protocol conversion delay and the end-to-end delay requirement of the message; According to the delay margin and network resource status, generate a feedforward compensation strategy for high-priority messages with a delay margin less than the threshold to form a delay compensation strategy.

5. The method according to claim 4, wherein Form a delay compensation strategy, including: Read the delay margin and priority tag of the message, and classify the message into high, medium, and low sensitivity levels; For high-sensitivity messages, calculate the minimum processing resource requirements required to ensure that their conversion delay does not exceed the delay margin; According to the current system resources and the contribution weights of each resource to reducing the conversion delay, construct a resource-delay sensitivity matrix and calculate the optimal resource allocation scheme; based on this, combine the protocol type, message complexity, and minimum processing resource requirements of the message to select the most suitable conversion path; Integrate the resource allocation scheme and conversion path selection to generate a complete delay compensation strategy.

6. The method according to claim 1, characterized in that, Obtain the optimized conversion result, including: According to the delay compensation strategy, determine a suitable protocol conversion processing mode for each message to form a conversion mode decision and calculate the allowed processing time; Acquire and analyze the protocol structure of the target message, and identify the key semantic set and the non-key semantic set in the message accordingly; calculate the processing time of the key semantic set and the remaining time budget for processing the non-key semantic set in combination with the allowed processing time; Based on the remaining time budget, an important reserved subset is extracted from the non-critical semantic set, and combined with the critical semantic set to generate a semantic pruning scheme; Protocol conversion is performed according to the semantic tailoring scheme, key semantic sets are prioritized, and optimized conversion results are generated.

7. The method according to claim 6, characterized in that, Identify key and non-key semantic sets in the message, including: Read the protocol type and message type of the target message, and extract the complete semantic structure diagram of the message of this type; According to the current business scenario and control requirements, identify the necessary functional fields from the complete semantic structure diagram; Analyze the application context of the target message in the current business environment and identify the associated status fields required for interaction with other systems from the complete semantic structure diagram; The necessary function fields and associated status fields are combined to form the key semantic set of the message and assign weights, and the remaining fields in the complete semantic structure diagram are classified into the non-key semantic set.

8. The method according to claim 6, characterized in that, Generate semantic pruning solutions, including: Based on the semantic importance scores in the key semantic set and the estimated processing time of each field, a performance-semantics trade-off function is constructed to maximize the amount of semantic information retained under time constraints. Call the performance-semantics trade-off function to select the most important subset from the non-critical semantic set so that its processing time does not exceed the remaining time budget, and generate the non-critical semantic retention subset; Integrate the key semantic set and the non-key semantic retained subset to form a semantic pruning scheme, which includes all the fields that need to be retained and their processing priorities.

9. The method according to claim 8, wherein It also includes monitoring the real-time processing delay during protocol conversion and making delay control adjustments: Read the real-time processing delay data of the current protocol conversion process, calculate the deviation from the expected protocol conversion delay, and obtain the delay deviation value; When it exceeds the delay deviation threshold, the feedback adjustment process is triggered; Analyze the positive and negative direction and magnitude of the delay deviation value to determine whether the current delay condition is exceeding expectations or resource redundancy; In case of delay exceeding expectations, adjust the semantic pruning plan, streamline the non-critical semantic retention subset, and apply for emergency processing resources; In case of resource redundancy, the non-critical semantic reserved subset is expanded and the excess resources are released.

10. The method according to claim 1, characterized in that, Generate the optimal topology reconstruction plan, including: Based on the multi-scale delay feature model and real-time processing delay data, the delay bottlenecks and congestion areas in the current network topology are identified, and the network optimization objective function is constructed in combination with the end-to-end delay requirements of each service flow in the substation; Based on the network optimization objective function, a set of candidate topology reconstruction solutions is generated, including link adjustment, traffic redistribution and protocol conversion node deployment strategies; Evaluate the impact of each candidate topology reconstruction scheme on the latency of key business flows, generate scheme evaluation results, and select the scheme with the highest comprehensive score as the optimal topology reconstruction scheme.

Images