Railway operation and maintenance communication network optimization system fusing power grid information

Abstract

The invention relates to the technical field of railway operation and maintenance communication, and discloses a railway operation and maintenance communication network optimization system fusing power grid information. The system comprises a multi-source data fusion module for collecting power, railway and environment data to generate a space-time multi-dimensional data cube; the communication quality evaluation module is used for analyzing data by using a fuzzy logic fusion algorithm to obtain a communication link quality degradation index sequence; the network topology optimization module is used for constructing a dynamic Bayesian network model to calculate an optimal communication routing table; the dynamic resource scheduling module is used for designing a bilevel programming algorithm to realize frequency spectrum and power joint scheduling; and the exception collaborative processing module is used for establishing a federated learning framework to generate a cross-domain collaborative repair instruction set. The system can accurately evaluate communication quality, optimize network topology, reasonably dispatch resources and cooperatively process exceptions by fusing power grid information, and effectively improves the performance and reliability of a railway operation and maintenance communication network.

Description

Technical Field

[0001] The present invention relates to the field of railway operation and maintenance communication technology, and in particular to a railway operation and maintenance communication network optimization system integrating power grid information. Background Art

[0002] The stable operation of the railway operation and maintenance communication network is crucial in railway transportation systems. It not only transmits critical information such as train scheduling and equipment status monitoring, but is also closely linked to safe railway operations. However, the current railway operation and maintenance communication network faces numerous challenges in its actual operation.

[0003] On the one hand, communication networks and the power grid environment interact in complex ways. Fluctuations in power load can generate electromagnetic interference, affecting the quality of communication signals. For example, during peak periods, the power system's harmonic content increases. These harmonics can couple into communication lines, causing signal errors and attenuation, and in severe cases, even communication interruptions. Furthermore, changes in the power grid topology can cause instability in the communication network. When the power grid undergoes equipment maintenance or fault isolation, the electromagnetic environment changes, disrupting the transmission path and quality of communication signals.

[0004] On the other hand, traditional resource scheduling methods for railway operation and maintenance communication networks are relatively crude. Spectrum resource allocation is often based on fixed rules or empirical evidence, failing to fully consider the dynamic changes in real-time grid load and communication demand. This results in spectrum resources being either idle and wasted or underallocated during certain periods or regions, failing to meet the actual needs of communication services. Furthermore, power allocation lacks effective and balanced management of base station energy consumption. This can lead to premature failure of some base stations due to prolonged high-power operation, increasing maintenance costs and operational risks.

[0005] Furthermore, when anomalies occur in the railway operation and maintenance communication network, existing handling mechanisms are significantly inadequate. Communication and power grid failures are often interrelated, but there is currently a lack of effective means to simultaneously detect and collaboratively handle both types of failures. The independence of various systems prevents rapid sharing of fault information, resulting in inefficient fault handling and long recovery times, seriously impacting the normal operation of railway transportation. Furthermore, with the continuous expansion of railway transportation services, such as the popularization of high-speed trains and the development of intelligent transportation systems, the performance requirements for railway operation and maintenance communication networks are becoming increasingly stringent. Existing communication network optimization technologies struggle to adapt to these new demands and are unable to achieve deep integration of communication network and power grid information. This makes them inadequate in ensuring communication quality, improving resource utilization, and addressing complex failures. Summary of the Invention

[0006] The purpose of the present invention is to provide a railway operation and maintenance communication network optimization system that integrates power grid information to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a railway operation and maintenance communication network optimization system integrating power grid information, the system comprising:

[0008] A multi-source data fusion module is used to synchronously collect power load fluctuations, grid topology status, rail vibration spectrum, communication signal strength, and environmental meteorological data through heterogeneous sensors to generate a spatiotemporal multidimensional data cube;

[0009] a communication quality assessment module, configured to perform nonlinear correlation analysis on the spatiotemporal multidimensional data cube using a fuzzy logic fusion algorithm to generate a communication link quality degradation index sequence;

[0010] A network topology optimization module is used to construct a path planning model based on a dynamic Bayesian network and calculate the optimal communication routing table under power interference conditions according to the degradation index sequence;

[0011] The dynamic resource scheduling module is used to design a resource allocation algorithm based on two-level planning, combining the real-time grid load and communication demand forecasts to generate a joint spectrum and power scheduling strategy;

[0012] The abnormal collaborative processing module is used to establish a distributed federated learning framework and generate a cross-domain collaborative repair instruction set based on the power grid fault characteristics and communication interruption patterns.

[0013] Preferably, the implementation of the multi-source data fusion module includes:

[0014] Perform time and space stamp alignment on heterogeneous data streams and eliminate sensor sampling rate differences through a sliding window mechanism;

[0015] Construct a fuzzy logic rule base to map the power grid harmonic distortion rate and communication bit error rate into membership vectors;

[0016] The evidence theory synthesis algorithm is used to weight the credibility of conflicting data and output a dimensionality-reduced fusion feature matrix.

[0017] Preferably, the construction of the communication quality assessment module includes:

[0018] The input variables of the fuzzy inference system are defined as signal attenuation gradient, multipath delay spread and grid harmonic injection energy;

[0019] Define Gaussian membership functions to describe the degradation trend of each variable and generate a three-dimensional regular surface;

[0020] The key degradation modes are extracted by the λ-cut set method, and the communication link quality level classification results are output.

[0021] Preferably, the design of the network topology optimization module includes:

[0022] Map substation nodes and communication relay stations into a two-layer node structure of Bayesian network;

[0023] The conditional probability distribution table of power grid power flow mutation events on communication bit error rate is calculated, and the Markov chain Monte Carlo sampling algorithm is used to solve the maximum a posteriori probability path to generate an anti-interference routing strategy.

[0024] Preferably, the implementation of the dynamic resource scheduling module includes:

[0025] An upper-level model is established to minimize grid harmonic interference and optimize the communication frequency band selection strategy. A lower-level model is constructed to balance base station energy consumption and solve the Pareto frontier of power allocation.

[0026] The alternating direction multiplier method is used to iteratively solve the two-layer model and output a spectrum-power joint configuration scheme.

[0027] Preferably, the establishment of the abnormal collaborative processing module includes:

[0028] A lightweight fault diagnosis model is trained on local nodes to extract the latent variable relationship between power grid transient characteristics and communication packet loss patterns. A model aggregation protocol is designed to fuse the gradient updates of each node through a differential privacy protection mechanism.

[0029] Generate a collaborative repair decision tree that includes fault isolation instructions and channel switching strategies.

[0030] Preferably, the network topology optimization module further includes:

[0031] Build a real-time topology update mechanism to capture transient changes in the power grid topology through a sliding time window;

[0032] A prediction and correction algorithm based on Kalman filtering is defined to dynamically correct the path delay estimation value in the communication routing table, and a taboo search strategy is used to quickly locate the suboptimal routing solution in the preset solution space, and generate dynamic path switching instructions that are resistant to sudden interference.

[0033] Preferably, the system further comprises:

[0034] Build a spatiotemporal correlation database and use tensor decomposition algorithm to mine cross-domain correlation rules between historical power grid events and communication failures;

[0035] Define a rule engine to match current data patterns in real time and generate a queue of preventive maintenance recommendations.

[0036] Preferably, the system further comprises:

[0037] Deploy edge computing node clusters and use a streaming computing framework to achieve end-to-end latency compression for data collection and decision generation;

[0038] Define a priority scheduling algorithm to dynamically allocate computing resources to handle optimization tasks of different urgency.

[0039] Preferably, the present invention further includes a method for optimizing a railway operation and maintenance communication network integrating power grid information, the method comprising the following steps:

[0040] Step 1: Use heterogeneous sensors to synchronously collect power load fluctuations, grid topology status, rail vibration spectrum, communication signal strength, and environmental meteorological data to generate a spatiotemporal multidimensional data cube.

[0041] Step 2: Using a fuzzy logic fusion algorithm to perform nonlinear correlation analysis on the spatiotemporal multidimensional data cube to generate a communication link quality degradation index sequence;

[0042] Step 3: Construct a path planning model based on a dynamic Bayesian network, and calculate the optimal communication routing table under power interference conditions according to the degradation index sequence;

[0043] Step 4: Design a resource allocation algorithm based on bi-level planning, combining the real-time grid load and communication demand forecasts to generate a joint spectrum and power scheduling strategy.

[0044] Step 5: Establish a distributed federated learning framework to generate a cross-domain collaborative repair instruction set based on the grid fault characteristics and communication interruption patterns.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] From a data fusion perspective, the multi-source data fusion module uses heterogeneous sensors to synchronously collect multiple data types, such as power load fluctuations and grid topology status, and generates a spatiotemporal multidimensional data cube. This process organically integrates data from different fields, providing a comprehensive data foundation for subsequent precise analysis and decision-making. It overcomes the limitations of traditional systems that rely solely on a single data type for analysis, enabling a more comprehensive and accurate understanding of the operating status of the railway operation and maintenance communication network and the power grid. For example, by integrating grid harmonic distortion rate data with communication bit error rate data, the potential connections between the two can be deeply explored, providing strong support for communication quality assessment and fault prediction.

[0047] For communication quality assessment, a fuzzy logic fusion algorithm is used to generate a series of communication link quality degradation indices. This method fully considers the nonlinear relationships between multiple influencing factors, such as signal attenuation gradient, multipath delay spread, and grid harmonic injection energy. Compared with traditional simple evaluation methods, it can more accurately reflect the actual quality of the communication link. This helps to promptly identify potential problems in the communication link, allowing for proactive optimization and maintenance measures, reducing the probability of communication failures and ensuring stable and reliable railway communications.

[0048] The network topology optimization module builds a path planning model based on a dynamic Bayesian network to calculate the optimal communication routing table under power interference conditions. This enables the communication network to dynamically adjust routing based on the real-time status of the power grid, effectively avoiding areas where communication quality degrades due to power interference and improving communication's anti-interference capabilities. Even in the event of unexpected power grid conditions, such as sudden changes in power flow, the system can quickly find the optimal or suboptimal route, ensuring communication continuity and preventing disruptions that could impact railway transportation safety.

[0049] The dynamic resource scheduling module utilizes a two-tiered resource allocation algorithm, combining real-time grid load and predicted communication demand to generate a joint spectrum and power scheduling strategy. This upper-tier model optimizes communication frequency band selection to minimize grid harmonic interference. Furthermore, the lower-tier model solves power allocation based on balanced base station energy consumption, improving resource utilization efficiency and reducing operating costs. For example, while meeting communication needs, the module rationally allocates spectrum and power resources, avoiding overuse of certain frequency bands and base stations and extending equipment life.

[0050] The Collaborative Anomaly Processing module establishes a distributed federated learning framework and generates a set of cross-domain collaborative repair instructions. This module breaks down the information barriers between the communication and power systems, enabling collaborative analysis and processing of grid fault characteristics and communication interruption patterns. When an anomaly occurs, it can quickly develop and execute cross-domain collaborative repair strategies, such as promptly isolating the faulty area and switching communication channels. This significantly shortens fault handling time and improves the reliability and stability of the railway operation and maintenance communication network.

[0051] Furthermore, the system's built-in spatiotemporal correlation database and rules engine can mine cross-domain correlation rules between historical power grid events and communication failures, generating preventative maintenance recommendations. This helps identify potential failure risks in advance, enabling preventive measures to reduce the frequency and scope of failures. The deployment of edge computing node clusters and priority scheduling algorithms achieves end-to-end latency reduction between data collection and decision generation, enabling rapid response to urgent optimization tasks and further improving the system's real-time performance and overall performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1This is a working principle diagram of the railway operation and maintenance communication network optimization system integrating power grid information according to the present invention;

[0053] Figure 2 This is the working principle diagram of the communication quality assessment module;

[0054] Figure 3 This is the working principle diagram of the dynamic resource scheduling module;

[0055] Figure 4 A diagram showing how the extended functionality for the Network Topology Optimization module works. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0057] See also Figure 1-Figure 4 The present invention provides a railway operation and maintenance communication network optimization system that integrates power grid information. The overall implementation scheme is as follows:

[0058] Multi-source data fusion: Heterogeneous sensors are used to simultaneously collect data on power load fluctuations, grid topology, rail vibration spectrum, communication signal strength, and environmental meteorological conditions, generating a spatiotemporal multidimensional data cube. These sensors are distributed along the railway and around related power facilities, enabling real-time acquisition of various critical data.

[0059] Communication quality assessment: A fuzzy logic fusion algorithm is used to perform nonlinear correlation analysis on the generated spatiotemporal multidimensional data cube, ultimately generating a communication link quality degradation index sequence to accurately assess the quality status of the communication link.

[0060] Network topology optimization: Build a path planning model based on a dynamic Bayesian network. Based on the communication link quality degradation index sequence, calculate the optimal communication routing table under power interference conditions, thereby optimizing the network topology and ensuring communication stability.

[0061] Dynamic resource scheduling: Design a resource allocation algorithm based on two-level planning. Combined with the real-time grid load and communication demand forecast, a joint spectrum and power scheduling strategy is generated to achieve the rational allocation of communication resources.

[0062] Collaborative abnormality processing: Establish a distributed federated learning framework to generate a cross-domain collaborative repair instruction set based on power grid fault characteristics and communication interruption patterns, so that abnormal situations can be handled quickly and effectively.

[0063] The implementation of the present invention will be further described below with reference to Examples 1 to 5.

[0064] Example 1:

[0065] This example focuses on the specific implementation of a multi-source data fusion module. In practical applications, a large number of different types of sensors are distributed along railway lines, including those monitoring power load, devices monitoring grid topology, sensors capturing rail vibration spectra, devices detecting communication signal strength, and instruments collecting environmental and meteorological data. Due to differences in manufacturer, model, and function, the data streams output by these sensors may have inconsistent time and space stamps and varying sampling rates.

[0066] To address these issues, we first align the time and space stamps of heterogeneous data streams. By adding precise time stamps to each sensor data point and arranging it in chronological order, we ensure temporal consistency across data from different sources. Furthermore, we utilize a sliding window mechanism to eliminate differences in sensor sampling rates. The sliding window size is set based on the actual data and system performance requirements, for example, to N sampling points. During this sliding process, data with different sampling rates are interpolated or decimated to fuse them on the same time scale.

[0067] Building a fuzzy logic rule base is one of the key steps in multi-source data fusion. In actual operation, there is a complex nonlinear relationship between the power grid harmonic distortion rate and the communication bit error rate. The power grid harmonic distortion rate is denoted as , the communication bit error rate is recorded as , through a large amount of experimental data and expert experience, fuzzy logic rules are established to and Mapped to membership vector. For example, define fuzzy subsets as "low", "medium" and "high". and The values ​​of determine their membership to each fuzzy subset.

[0068] The credibility of conflicting data is weighted by using the evidence theory synthesis algorithm. Assume there are two sources of evidence and , their credibility for a proposition is and (in is a proposition in the proposition set), then according to the evidence theory synthesis formula

[0069]

[0070] Calculate the credibility of the fusion In this system, different sensors may have conflicting measurements of the same physical quantity. This algorithm processes conflicting data, effectively improving data reliability. Ultimately, it outputs a dimensionality-reduced fusion feature matrix, providing high-quality data support for subsequent operations such as communication quality assessment.

[0071] Example 2:

[0072] This embodiment focuses on the construction process of the communication quality assessment module. In the railway operation and maintenance communication network, the quality of the communication link is affected by many factors, such as signal attenuation gradient, multipath delay spread, and grid harmonic injection energy. Therefore, the input variable of the fuzzy inference system is defined as the signal attenuation gradient. , multipath delay spread and grid harmonic injection energy .

[0073] In order to accurately describe the degradation trend of each variable, the Gaussian membership function is used. The expression of the Gaussian membership function is: ,in is the variable value, is the central value of the membership function, is the standard deviation. For example, for the signal attenuation gradient , determine the central value of its membership function based on historical data and actual experience and standard deviation , when the signal attenuation gradient is When , its membership degree is .

[0074] Similarly, for multipath delay spread and grid harmonic injection energy The corresponding Gaussian membership functions are also determined respectively.

[0075] A three-dimensional regular surface is generated using the membership functions of these three variables. In practice, fuzzy rules are formulated based on extensive experimental data and communication theory. For example, when the signal attenuation gradient is "high," the multipath delay spread is "large," and the grid harmonic injection energy is "strong," the communication link quality is "poor." These rules are applied to three-dimensional space to form a three-dimensional regular surface.

[0076] Finally, the key degradation modes are extracted by the λ-cut method. The λ-cut method is a commonly used method in fuzzy sets. Let the fuzzy set , its λ-cut set ,in for right In this embodiment, by adjusting the value of λ, key degradation patterns are extracted from the three-dimensional regular surface, and the communication link quality classification results are output. The communication link quality is divided into different levels such as "excellent", "good", "medium", and "poor", providing an important basis for subsequent network optimization.

[0077] Example 3:

[0078] This example focuses on the design details of the network topology optimization module. In the scenario of integrating the railway operation and maintenance communication network with the power grid, substation nodes and communication relay stations are mapped into a two-layer node structure of a Bayesian network. Substation nodes primarily reflect the operating status of the power grid, while communication relay station nodes are responsible for transmitting communication signals. In a Bayesian network, probabilistic dependencies exist between nodes.

[0079] Calculating the conditional probability distribution table of the power grid flow mutation event on the communication bit error rate is an important part of network topology optimization. Assume that the power grid flow mutation event is , the communication bit error rate is , through the analysis and statistics of a large amount of historical data, the conditional probability distribution is obtained For example, when the power flow sudden change degree is When the communication bit error rate is The probability of .

[0080] The Markov chain Monte Carlo sampling algorithm is used to solve the maximum a posteriori probability path. The Markov chain Monte Carlo sampling algorithm is a method for sampling in probability space. By constructing a Markov chain, its stationary distribution is the target distribution, thereby achieving sampling of the target distribution. In this embodiment, the algorithm is used to find the maximum a posteriori probability path in the Bayesian network. Let the path be , the posterior probability is (in is the observed data), and by continuous iterative sampling, we can find The largest path,generates an interference-resistant routing strategy.

[0081] In addition, the network topology optimization module also builds a real-time topology update mechanism. The transient change characteristics of the power grid topology are captured by sliding time windows, and the duration of the sliding time window is set to In each time window, the changes of the power grid topology are monitored and analyzed. At the same time, a prediction and correction algorithm based on Kalman filtering is defined to dynamically correct the path delay estimation value in the communication routing table. Assume that the estimated value of the path delay is The actual measured value is , according to the Kalman filter formula (in is the Kalman gain, A tabu search strategy is used to quickly locate suboptimal routing solutions within the preset solution space. When the primary route fails or is severely interfered with, it can quickly switch to the suboptimal route and generate dynamic path switching instructions to resist sudden interference, ensuring communication continuity.

[0082] Example 4:

[0083] This embodiment elaborates on the implementation process of the dynamic resource scheduling module. In the actual operation of the railway operation and maintenance communication network, the rational allocation of communication resources is the key link to ensure the communication effect and overall system performance, and the dynamic resource scheduling module is the core component to achieve this goal.

[0084] The communication network along railways is distributed with multiple base stations, and the communication demands and grid load conditions in different areas are constantly changing. To achieve the joint optimization of spectrum and power scheduling, an effective algorithm mechanism is needed.

[0085] First, the upper layer model is established, which optimizes the communication frequency band selection strategy with the goal of minimizing the harmonic interference of the power grid. In actual applications, there are many communication frequency bands to choose from, and these frequency bands are referred to as the set , different frequency bands are affected by power grid harmonic interference to different degrees, set the frequency band The harmonic interference value of the power grid is Through the analysis of historical data and real-time monitoring, the interference values ​​of different frequency bands under different power grid operating conditions are obtained. When selecting the communication frequency band, these interference values ​​are comprehensively considered and the frequency band with smaller interference values ​​is selected as much as possible to reduce the impact of power grid harmonics on communication and ensure communication quality. For example, after calculation and comparison, 、 、 、 The size of Minimum, then in the current situation, the frequency band is preferred .

[0086] Next, we build a lower-level model, which uses the balanced base station energy consumption as a constraint to solve the power allocation scheme. Each base station consumes a certain amount of energy when transmitting signals, and different power allocation methods will result in different base station energy consumption. Let the base station set be , base station The power is , its energy consumption is related to power, assuming that energy consumption and power Satisfy the linear relationship (in For base stations To ensure the balance of base station energy consumption in the entire communication network and prevent some base stations from being damaged prematurely or experiencing performance degradation due to excessive energy consumption, the total energy consumption limit is set to , that is, the need to satisfy Under these constraints, power is allocated appropriately based on the communication needs of different base station coverage areas. For example, power allocation is appropriately increased for base stations in areas with high communication demand, while power is reduced for base stations in areas with low communication demand. This ensures balanced energy consumption across base stations while ensuring communication quality.

[0087] The alternating direction multiplier method is used to iteratively solve the two-layer model. This method decomposes the complex two-layer optimization problem into relatively simple subproblems for solution. During the iterative process, the power allocation scheme of the lower-layer model is first fixed, and the communication frequency band selection is optimized according to the objectives of the upper-layer model. Then, the communication frequency band selected by the upper-layer model is fixed, and the power allocation scheme is adjusted according to the constraints of the lower-layer model. This iterative process continuously optimizes the communication frequency band and power allocation. Each iteration improves the communication frequency band selection to reduce grid harmonic interference and the power allocation to balance base station energy consumption. After multiple iterations, a combined spectrum-power allocation solution is ultimately output, achieving efficient utilization of communication resources and improving the overall performance of the railway operation and maintenance communication network.

[0088] Example 5:

[0089] This embodiment mainly introduces the establishment of the abnormal collaborative processing module and the implementation of other functions of the system. In the abnormal collaborative processing module, a lightweight fault diagnosis model is trained at the local node. The machine learning algorithm is used to train the model using the locally collected power grid transient feature data and communication packet loss pattern data. Assume that the power grid transient feature vector is , the communication packet loss pattern vector is , through training, a latent variable relationship model between the two is established.

[0090] Design a model aggregation protocol to integrate the gradient updates of each node through the differential privacy protection mechanism. Under the distributed federated learning framework, each local node uploads the gradient updates obtained from training to the central server. To protect data privacy, a differential privacy protection mechanism is adopted. The gradient update amount is , add noise ( Obey a specific noise distribution) and then upload, that is, the uploaded gradient update amount is The central server integrates the gradient updates uploaded by each node according to the model aggregation protocol and updates the global model.

[0091] Generate a collaborative repair decision tree that includes fault isolation instructions and channel switching strategies. Based on the trained model and the fused gradient update, a corresponding collaborative repair decision tree is generated when grid fault characteristics or communication interruption patterns are detected. For example, if a regional grid fault is detected, resulting in communication interruption, the decision tree outputs fault isolation instructions to isolate the faulty area and generates a channel switching strategy to switch communications to a backup channel to ensure normal communication.

[0092] In addition, the system also builds a spatiotemporal correlation database and uses tensor decomposition algorithm to mine cross-domain correlation rules between historical power grid events and communication failures. Assume that the historical power grid event data tensor is , the communication failure data tensor is , through the tensor decomposition algorithm (in 、 、 is the low-dimensional tensor after decomposition, is the rank of the decomposition, (a tensor outer product operation) to mine association rules between the two. A rule engine is defined to match current data patterns in real time. When the current data pattern matches the mined association rules, a preventive maintenance recommendation queue is generated, allowing proactive measures to prevent failures.

[0093] The system also deploys a cluster of edge computing nodes and uses a streaming computing framework to achieve end-to-end latency compression for data collection and decision generation. Edge computing nodes are distributed along the railway line and can collect data in real time and perform preliminary processing. A streaming computing framework, such as Apache Flink, is used to process the collected data in real time and quickly generate decisions. A priority scheduling algorithm is defined to dynamically allocate computing resources based on the urgency of the optimization task. Suppose the set of optimization tasks is , the urgency of each task is ( ), sort tasks according to their urgency, prioritize computing resources to handle urgent tasks, and improve the system's response speed and performance.

[0094] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0095] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A railway operation and maintenance communication network optimization system integrating power grid information, characterized in that: The system comprises: A multi-source data fusion module is used to synchronously collect power load fluctuations, grid topology status, rail vibration spectrum, communication signal strength, and environmental meteorological data through heterogeneous sensors to generate a spatiotemporal multidimensional data cube; a communication quality assessment module, configured to perform nonlinear correlation analysis on the spatiotemporal multidimensional data cube using a fuzzy logic fusion algorithm to generate a communication link quality degradation index sequence; A network topology optimization module is used to construct a path planning model based on a dynamic Bayesian network and calculate the optimal communication routing table under power interference conditions according to the degradation index sequence; Dynamic resource scheduling module, used to design a resource allocation algorithm based on two-level planning, combining the real-time grid load and communication demand forecast to generate a joint spectrum and power scheduling strategy; The abnormal collaborative processing module is used to establish a distributed federated learning framework and generate a cross-domain collaborative repair instruction set based on the power grid fault characteristics and communication interruption patterns.

2. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The implementation of the multi-source data fusion module includes: Perform time and space stamp alignment on heterogeneous data streams and eliminate sensor sampling rate differences through a sliding window mechanism; Construct a fuzzy logic rule base to map the power grid harmonic distortion rate and communication bit error rate into membership vectors; The evidence theory synthesis algorithm is used to weight the credibility of conflicting data and output a dimensionality-reduced fusion feature matrix.

3. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The construction of the communication quality assessment module includes: The input variables of the fuzzy inference system are defined as signal attenuation gradient, multipath delay spread and grid harmonic injection energy; Define Gaussian membership functions to describe the degradation trend of each variable and generate a three-dimensional regular surface; The key degradation modes are extracted by the λ-cut set method, and the communication link quality level classification results are output.

4. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The design of the network topology optimization module includes: Map substation nodes and communication relay stations into a two-layer node structure of Bayesian network; The conditional probability distribution table of power grid power flow mutation events on communication bit error rate is calculated, and the Markov chain Monte Carlo sampling algorithm is used to solve the maximum a posteriori probability path to generate an anti-interference routing strategy.

5. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The implementation of the dynamic resource scheduling module includes: An upper-level model is established to minimize grid harmonic interference and optimize the communication frequency band selection strategy. A lower-level model is constructed to balance base station energy consumption and solve the Pareto frontier of power allocation. The alternating direction multiplier method is used to iteratively solve the two-layer model and output a spectrum-power joint configuration scheme.

6. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The establishment of the abnormal collaborative processing module includes: A lightweight fault diagnosis model is trained on local nodes to extract the latent variable relationship between power grid transient characteristics and communication packet loss patterns. A model aggregation protocol is designed to fuse the gradient updates of each node through a differential privacy protection mechanism. Generate a collaborative repair decision tree that includes fault isolation instructions and channel switching strategies.

7. The railway operation and maintenance communication network optimization system according to claim 4, characterized in that: The network topology optimization module also includes: Build a real-time topology update mechanism to capture transient changes in the power grid topology through a sliding time window; A prediction and correction algorithm based on Kalman filtering is defined to dynamically correct the path delay estimation value in the communication routing table, and a taboo search strategy is used to quickly locate the suboptimal routing solution in the preset solution space, and generate dynamic path switching instructions that are resistant to sudden interference.

8. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The system further comprises: Build a spatiotemporal correlation database and use tensor decomposition algorithm to mine cross-domain correlation rules between historical power grid events and communication failures; Define a rule engine to match current data patterns in real time and generate a queue of preventive maintenance recommendations.

9. The railway operation and maintenance communication network optimization system according to claim 1, characterized in that: The system further comprises: Deploy edge computing node clusters and use a streaming computing framework to achieve end-to-end latency compression for data collection and decision generation; Define a priority scheduling algorithm to dynamically allocate computing resources to handle optimization tasks of different urgency.

10. A railway operation and maintenance communication network optimization method integrating power grid information, characterized in that: The method comprises the following steps: Step 1: Use heterogeneous sensors to synchronously collect power load fluctuations, grid topology status, rail vibration spectrum, communication signal strength, and environmental meteorological data to generate a spatiotemporal multidimensional data cube. Step 2: Using a fuzzy logic fusion algorithm to perform nonlinear correlation analysis on the spatiotemporal multidimensional data cube to generate a communication link quality degradation index sequence; Step 3: Construct a path planning model based on a dynamic Bayesian network, and calculate the optimal communication routing table under power interference conditions according to the degradation index sequence; Step 4: Design a resource allocation algorithm based on bi-level planning, combining the real-time grid load and communication demand forecasts to generate a joint spectrum and power scheduling strategy. Step 5: Establish a distributed federated learning framework to generate a cross-domain collaborative repair instruction set based on the grid fault characteristics and communication interruption patterns.

Images