A Method and System for Energy Consumption Analysis of Highway Power Equipment Based on Intelligent Gateway

Abstract

This invention discloses a method and system for energy consumption analysis of highway power equipment based on smart gateways. The method includes: acquiring power equipment operation data collected by smart gateways deployed at multiple nodes along the highway; identifying operational energy consumption correlation characteristics corresponding to each smart gateway based on a preset correlation model; predicting the gateway area risk corresponding to each smart gateway based on the operational energy consumption correlation characteristics using a prediction model; and performing energy consumption structure analysis on the highway and identifying abnormal energy consumption data based on the gateway area risk, thereby outputting operational management suggestions for the power equipment. Therefore, this invention can achieve digital monitoring and risk warning of the operational status of highway power infrastructure, thus providing scientific decision-making suggestions and data support for the precise operation and management of power equipment.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for analyzing the energy consumption of highway power equipment based on a smart gateway. Background Technology

[0002] With the digital transformation of highway electromechanical systems and power distribution networks, achieving efficient condition monitoring and energy consumption management for the widely distributed highway power infrastructure has become a crucial technological direction for ensuring the safe operation of highways. However, existing highway power monitoring technologies typically rely on periodic on-site manual inspections or basic sensor data collection. The lack of technical support for acquiring operational data from intelligent gateways deployed at multiple nodes along the highway and using correlation models to identify operational energy consumption correlation characteristics makes it impossible to determine gateway area risks based on predictive models for energy consumption structure analysis and anomaly identification. This hinders the digital monitoring and risk warning of highway power infrastructure operation status, leading to insufficient accuracy in power equipment operation management and scientific decision-making. Undetected energy consumption anomalies or potential risks can easily cause power system failures, limiting the level of intelligent management and operational reliability of highway power infrastructure. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for energy consumption analysis of highway power equipment based on a smart gateway, which can realize digital monitoring and risk warning of the operation status of highway power infrastructure, thereby providing scientific decision-making suggestions and data support for the precise operation and management of power equipment.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a method for analyzing the energy consumption of highway power equipment based on a smart gateway, the method comprising: The system acquires power equipment operation data collected by intelligent gateways deployed at multiple nodes along the highway; these nodes include tunnels, toll stations, monitoring centers, and service areas. Based on a preset association model, identify the operating energy consumption association characteristics corresponding to each smart gateway. Based on the prediction model, and according to the operational energy consumption correlation characteristics, the gateway area risk corresponding to each smart gateway is predicted. Based on the risks in the gateway area, energy consumption structure analysis is performed on the highway and abnormal energy consumption data is identified to output operation and management recommendations for power equipment.

[0005] As an optional implementation, in the first aspect of the invention, the association model is established through the following steps: Obtain the operating status data of the power equipment during historical periods and the synchronously collected raw energy consumption data; The operating status data and the original energy consumption data are aggregated in multiple dimensions to extract the operating condition feature components and energy consumption distribution components of each node under different operating conditions. Calculate the correlation coefficient between each of the operating condition characteristic components and the corresponding energy consumption distribution components; Based on the correlation coefficient, a mapping function between operating status and energy consumption level is established as the correlation model.

[0006] As an optional implementation, in the first aspect of the present invention, identifying the operating energy consumption correlation characteristics corresponding to each smart gateway based on a preset correlation model includes: Identify the operating status identifier and synchronous power acquisition characteristics of each device connected to the smart gateway from the power equipment operation data; The operating condition identifier and the power acquisition feature are input into the association model to match the energy consumption response benchmark of each of the connected devices in different time windows; Calculate the energy consumption offset vector of the energy acquisition feature relative to the energy consumption response benchmark; The energy consumption offset vectors corresponding to multiple downstream devices are aggregated at the gateway level to generate the operating energy consumption correlation features corresponding to each smart gateway.

[0007] As an optional implementation, in a first aspect of the invention, calculating the energy consumption offset vector of the energy harvesting characteristic relative to the energy consumption response reference includes: The energy acquisition features are input into a preset vectorization network algorithm to generate acquisition feature vectors in a high-dimensional feature space. The energy consumption response benchmark is embedded using the vectorized network algorithm to obtain the corresponding benchmark reference vector; Based on a preset vector distance algorithm, the spatial position difference between the acquired feature vector and the reference vector in each dimension is calculated; Based on the spatial location differences, the direction and magnitude are encoded to generate an energy consumption offset vector that reflects the amplitude of power fluctuations.

[0008] As an optional implementation, in the first aspect of the present invention, the step of predicting the gateway area risk corresponding to each smart gateway based on the predictive model and according to the operational energy consumption correlation characteristics includes: Obtain historical communication data for each smart gateway and regional parameters of the smart gateway's deployment location; The historical communication data is subjected to message statistical analysis to extract communication stability feature components that reflect the communication quality of the smart gateway. The operating energy consumption correlation features, the communication stability feature components, and the regional parameters are subjected to multi-dimensional feature fusion processing to generate a comprehensive evaluation feature vector corresponding to each smart gateway. The comprehensive assessment feature vector is input into a preset risk prediction model, and the risk prediction model is used to map the comprehensive assessment feature vector to a risk level in order to predict the gateway area risk corresponding to each smart gateway.

[0009] As an optional implementation, in the first aspect of the invention, the risk prediction model is trained through the following steps: Multiple sample datasets of the power system of the highway during its historical operating cycle are obtained; each sample dataset includes historical operating energy consumption correlation features, historical communication stability feature components, historical regional parameters, and corresponding measured risk level labels; The historical operating energy consumption correlation features and the historical communication stability feature components are input into a preset feature extraction network to extract the dynamic evolution features of different nodes in the time series. Based on the attention mechanism, the dynamic evolution features and the historical region parameters are weighted and fused to obtain a multi-dimensional fused feature vector corresponding to each sample dataset; The multidimensional fused feature vector is input into the risk prediction network to be trained for forward propagation to output the predicted risk result; Calculate the loss function value between the predicted risk result and the measured risk level label, and update the weight parameters of the risk prediction network based on the backpropagation algorithm until the loss function value converges to obtain the gateway area risk prediction model.

[0010] As an optional implementation, in the first aspect of the present invention, the step of performing energy consumption structure analysis on the highway and identifying abnormal energy consumption data based on the gateway area risk, so as to output operation and management recommendations for power equipment, includes: Real-time communication interaction data between each smart gateway and its adjacent smart gateways are obtained to construct a communication topology map of the highway power system. Based on a preset correlation analysis algorithm, the propagation and diffusion index of the gateway area risk in the communication topology map is calculated, and the historical fault correlation weights corresponding to each smart gateway are retrieved. By combining the propagation and diffusion indicators and the historical fault association weights, the energy consumption contribution of each node is traced to generate the energy consumption structure analysis results of the highway. Based on the energy consumption structure analysis results, abnormal energy consumption data exceeding the preset fluctuation threshold are identified, and the potential fault points of power equipment are mapped by combining the historical fault association weights, so as to output corresponding operation and management suggestions.

[0011] As an optional implementation, in the first aspect of the present invention, the historical fault association weight is determined through the following steps: Obtain all historical fault records of the highway power system within a preset historical period; Extract the set of faulty smart gateways involved in each of the historical fault records, and count the fault frequency of each smart gateway in the historical fault records; For any two smart gateways, calculate the number of times the two smart gateways co-occur in the same historical fault record; Calculate the ratio between the co-occurrence frequency and the total failure frequency of each smart gateway in the set of faulty smart gateways to obtain the primary association weight; The historical fault association weights for each smart gateway are obtained by weighting and summing the primary association weights with the preset fault severity factor.

[0012] A second aspect of this invention discloses a highway power equipment energy consumption analysis system based on a smart gateway, the system comprising: The acquisition module is used to acquire power equipment operation data collected by smart gateways deployed at multiple nodes on the highway; the nodes are tunnels, toll stations, monitoring centers, or service areas. The identification module is used to identify the operating energy consumption correlation characteristics of each smart gateway based on a preset association model. The prediction module is used to predict the gateway area risk corresponding to each smart gateway based on the prediction model and the operational energy consumption correlation characteristics. The management module is used to perform energy consumption structure analysis on the highway based on the risks of the gateway area and identify abnormal energy consumption data, so as to output operation and management suggestions for power equipment.

[0013] As an optional implementation, in a second aspect of the invention, the association model is established through the following steps: Obtain the operating status data of the power equipment during historical periods and the synchronously collected raw energy consumption data; The operating status data and the original energy consumption data are aggregated in multiple dimensions to extract the operating condition feature components and energy consumption distribution components of each node under different operating conditions. Calculate the correlation coefficient between each of the operating condition characteristic components and the corresponding energy consumption distribution components; Based on the correlation coefficient, a mapping function between operating status and energy consumption level is established as the correlation model.

[0014] As an optional implementation, in a second aspect of the present invention, the identification module identifies the specific method by which it identifies the operating energy consumption correlation characteristics corresponding to each smart gateway based on a preset association model, including: Identify the operating status identifier and synchronous power acquisition characteristics of each device connected to the smart gateway from the power equipment operation data; The operating condition identifier and the power acquisition feature are input into the association model to match the energy consumption response benchmark of each of the connected devices in different time windows; Calculate the energy consumption offset vector of the energy acquisition feature relative to the energy consumption response benchmark; The energy consumption offset vectors corresponding to multiple downstream devices are aggregated at the gateway level to generate the operating energy consumption correlation features corresponding to each smart gateway.

[0015] As an optional implementation, in a second aspect of the invention, the specific method by which the identification module calculates the energy consumption offset vector of the energy collection feature relative to the energy consumption response reference includes: The energy acquisition features are input into a preset vectorization network algorithm to generate acquisition feature vectors in a high-dimensional feature space. The energy consumption response benchmark is embedded using the vectorized network algorithm to obtain the corresponding benchmark reference vector; Based on a preset vector distance algorithm, the spatial position difference between the acquired feature vector and the reference vector in each dimension is calculated; Based on the spatial location differences, the direction and magnitude are encoded to generate an energy consumption offset vector that reflects the amplitude of power fluctuations.

[0016] As an optional implementation, in a second aspect of the invention, the prediction module, based on a prediction model and according to the operational energy consumption correlation characteristics, predicts the specific method by which it predicts the gateway area risk corresponding to each smart gateway, including: Obtain historical communication data for each smart gateway and regional parameters of the smart gateway's deployment location; The historical communication data is subjected to message statistical analysis to extract communication stability feature components that reflect the communication quality of the smart gateway. The operating energy consumption correlation features, the communication stability feature components, and the regional parameters are subjected to multi-dimensional feature fusion processing to generate a comprehensive evaluation feature vector corresponding to each smart gateway. The comprehensive assessment feature vector is input into a preset risk prediction model, and the risk prediction model is used to map the comprehensive assessment feature vector to a risk level in order to predict the gateway area risk corresponding to each smart gateway.

[0017] As an optional implementation, in a second aspect of the invention, the risk prediction model is trained through the following steps: Multiple sample datasets of the power system of the highway during its historical operating cycle are obtained; each sample dataset includes historical operating energy consumption correlation features, historical communication stability feature components, historical regional parameters, and corresponding measured risk level labels; The historical operating energy consumption correlation features and the historical communication stability feature components are input into a preset feature extraction network to extract the dynamic evolution features of different nodes in the time series. Based on the attention mechanism, the dynamic evolution features and the historical region parameters are weighted and fused to obtain a multi-dimensional fused feature vector corresponding to each sample dataset; The multidimensional fused feature vector is input into the risk prediction network to be trained for forward propagation to output the predicted risk result; Calculate the loss function value between the predicted risk result and the measured risk level label, and update the weight parameters of the risk prediction network based on the backpropagation algorithm until the loss function value converges to obtain the gateway area risk prediction model.

[0018] As an optional implementation, in a second aspect of the invention, the management module performs energy consumption structure analysis on the highway based on the gateway area risk and identifies abnormal energy consumption data to output operation and management recommendations for power equipment, including: Real-time communication interaction data between each smart gateway and its adjacent smart gateways are obtained to construct a communication topology map of the highway power system. Based on a preset correlation analysis algorithm, the propagation and diffusion index of the gateway area risk in the communication topology map is calculated, and the historical fault correlation weights corresponding to each smart gateway are retrieved. By combining the propagation and diffusion indicators and the historical fault association weights, the energy consumption contribution of each node is traced to generate the energy consumption structure analysis results of the highway. Based on the energy consumption structure analysis results, abnormal energy consumption data exceeding the preset fluctuation threshold are identified, and the potential fault points of power equipment are mapped by combining the historical fault association weights, so as to output corresponding operation and management suggestions.

[0019] As an optional implementation, in a second aspect of the invention, the historical fault association weights are determined through the following steps: Obtain all historical fault records of the highway power system within a preset historical period; Extract the set of faulty smart gateways involved in each of the historical fault records, and count the fault frequency of each smart gateway in the historical fault records; For any two smart gateways, calculate the number of times the two smart gateways co-occur in the same historical fault record; Calculate the ratio between the co-occurrence frequency and the total failure frequency of each smart gateway in the set of faulty smart gateways to obtain the primary association weight; The historical fault association weights for each smart gateway are obtained by weighting and summing the primary association weights with the preset fault severity factor.

[0020] A third aspect of this invention discloses another energy consumption analysis system for highway power equipment based on a smart gateway, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the energy consumption analysis method for highway power equipment based on a smart gateway disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the energy consumption analysis method for highway power equipment based on a smart gateway disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention acquires power equipment operation data collected by smart gateways deployed at multiple nodes of highways, identifies operational energy consumption correlation characteristics using an association model, and then determines the risks of gateway areas based on a prediction model for energy consumption structure analysis and anomaly identification. This enables digital monitoring and risk warning of the operational status of highway power infrastructure, thereby providing scientific decision-making suggestions and data support for the precise operation and management of power equipment. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a method for analyzing the energy consumption of highway power equipment based on a smart gateway, as disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of the structure of a highway power equipment energy consumption analysis system based on a smart gateway, as disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another energy consumption analysis system for highway power equipment based on a smart gateway, as disclosed in an embodiment of the present invention.

[0027] Figure 4 This is a schematic diagram of the structure of an intelligent communication management gateway disclosed in an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] This invention discloses a method and system for energy consumption analysis of highway power equipment based on smart gateways. By acquiring power equipment operation data collected from smart gateways deployed at multiple nodes along the highway, and using a correlation model to identify operational energy consumption correlation characteristics, the method further determines the risks in the gateway area based on a predictive model for energy consumption structure analysis and anomaly identification. This enables digital monitoring and risk warning of the operational status of highway power infrastructure, providing scientific decision-making suggestions and data support for the precise operation and management of power equipment. Detailed explanations follow.

[0032] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for analyzing the energy consumption of highway power equipment based on a smart gateway, as disclosed in an embodiment of the present invention. Figure 1 The described energy consumption analysis method for highway power equipment based on smart gateways can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 1 As shown, the energy consumption analysis method for highway power equipment based on a smart gateway may include the following operations: 101. Obtain power equipment operation data collected by smart gateways deployed at multiple nodes of the highway.

[0033] Optional nodes include tunnels, toll stations, monitoring centers, or service areas.

[0034] Optionally, the power equipment operating data may include transformer load rate, three-phase voltage and current imbalance, harmonic content, active power and reactive power, which are not limited in this invention.

[0035] 102. Based on the preset association model, identify the energy consumption association characteristics of each smart gateway.

[0036] 103. Based on the prediction model and the correlation characteristics of operating energy consumption, predict the gateway area risk corresponding to each smart gateway.

[0037] 104. Based on the risks in the gateway area, conduct energy consumption structure analysis on the highway and identify abnormal energy consumption data to output operation and management recommendations for power equipment.

[0038] As can be seen, the above-mentioned embodiments of the invention acquire power equipment operation data collected by smart gateways deployed at multiple nodes of highways, and use correlation models to identify the correlation characteristics of operating energy consumption. Then, based on prediction models, they determine the risks of gateway areas for energy consumption structure analysis and anomaly identification. This enables digital monitoring and risk warning of the operating status of highway power infrastructure, and provides scientific decision-making suggestions and data support for the precise operation management of power equipment.

[0039] As an optional embodiment, the association model in the above steps is established through the following steps: Acquire operating status data of power equipment within historical time periods and synchronously collect raw energy consumption data; Multi-dimensional aggregation processing is performed on the operating status data and raw energy consumption data to extract the operating condition feature components and energy consumption distribution components of each node under different operating conditions. Calculate the correlation coefficient between each operating condition characteristic component and the corresponding energy consumption distribution component; Based on the correlation coefficient, a mapping function between operating status and energy consumption level is established as a correlation model.

[0040] Optionally, the correlation coefficient can be calculated using Pearson correlation coefficient, Spearman rank correlation coefficient, or mutual information method, and can be used to quantify the linear or nonlinear relationship between device switching state and power consumption fluctuation.

[0041] As can be seen, through the above optional embodiments, by performing multi-dimensional aggregation and correlation analysis on historical operating data and energy consumption data, a precise mapping relationship between equipment operating conditions and energy consumption can be established, thereby providing a quantitative calculation model for subsequent energy consumption correlation feature extraction and enhancing the system's ability to perceive the energy consumption fluctuation patterns of power equipment.

[0042] As an optional embodiment, the step above, identifying the operating energy consumption correlation characteristics corresponding to each smart gateway based on a preset association model, includes: Identify the operating status identifiers and synchronous power acquisition characteristics of each smart gateway-connected device from the power equipment operation data; The operating condition identifier and power collection characteristics are input into the correlation model to match the energy consumption response benchmark of each downstream device in different time windows; Calculate the energy consumption offset vector of the energy acquisition characteristics relative to the energy consumption response benchmark; The energy consumption offset vectors corresponding to multiple downstream devices are aggregated at the gateway level to generate the operating energy consumption correlation features for each smart gateway.

[0043] Optionally, the operating condition indicator may include standby mode, full load mode, energy saving mode or fault protection mode, and the present invention does not limit it.

[0044] As can be seen, through the above optional embodiments, by matching the energy consumption response benchmark of the downstream equipment and the vector aggregation at the gateway dimension, it is possible to extract the correlation features that reflect the power operation pattern of the node, thereby improving the detection accuracy of abnormal power fluctuations on highways.

[0045] As an optional embodiment, the step of calculating the energy consumption offset vector of the energy collection characteristics relative to the energy consumption response benchmark in the above steps includes: The power acquisition features are input into a preset vectorization network algorithm to generate acquisition feature vectors in a high-dimensional feature space. The energy consumption response benchmark is embedded using a vectorized network algorithm to obtain the corresponding benchmark reference vector; Based on a preset vector distance algorithm, the spatial positional differences between the collected feature vector and the benchmark reference vector in each dimension are calculated. The direction and magnitude are encoded based on spatial location differences to generate an energy consumption offset vector that reflects the amplitude of power fluctuations.

[0046] Optionally, the vectorized network algorithm can employ a variant structure of an autoencoder or Word2Vec, which can map time-series acquired data into high-dimensional dense vectors.

[0047] As can be seen, through the above optional embodiments, by extracting high-dimensional features through vectorized network algorithms and combining them with vector distance algorithms to calculate spatial differences, it is possible to accurately quantify the subtle deviations between real-time collected features and the benchmark, thereby effectively improving the accuracy of describing and the sensitivity of identifying abnormal fluctuations in energy consumption under complex environments.

[0048] As an optional embodiment, the step above, predicting the gateway area risk corresponding to each smart gateway based on the prediction model and the associated characteristics of operating energy consumption, includes: Obtain historical communication data for each smart gateway and regional parameters of the smart gateway's deployment location; Message statistical analysis is performed on historical communication data to extract communication stability feature components that reflect the communication quality of the smart gateway. The operating energy consumption correlation features, communication stability feature components and regional parameters are subjected to multi-dimensional feature fusion processing to generate a comprehensive evaluation feature vector for each smart gateway. The comprehensive assessment feature vector is input into the preset risk prediction model. The risk prediction model maps the comprehensive assessment feature vector to risk levels to predict the gateway area risk corresponding to each smart gateway.

[0049] Optionally, area parameters may include ambient humidity, altitude, salt spray concentration, and physical distance to the nearest service center.

[0050] As can be seen, through the above optional embodiments, the correlation mapping between energy consumption anomalies and communication fluctuations is realized by integrating regional parameters and historical communication data, thereby improving the reliability of predicting the operational risks of highway power nodes.

[0051] As an optional embodiment, the risk prediction model in the above steps is trained through the following steps: Obtain multiple sample datasets of the power system of the highway during its historical operating cycle; optionally, each sample dataset includes historical operating energy consumption correlation features, historical communication stability feature components, historical regional parameters, and corresponding measured risk level labels; The historical energy consumption correlation features and historical communication stability features are input into a preset feature extraction network to extract the dynamic evolution features of different nodes over time. Based on the attention mechanism, dynamic evolution features and historical region parameters are weighted and fused to obtain a multi-dimensional fused feature vector corresponding to each sample dataset. The multidimensional fused feature vector is input into the risk prediction network to be trained for forward propagation to output the predicted risk result; The loss function value between the predicted risk result and the measured risk level label is calculated, and the weight parameters of the risk prediction network are updated based on the backpropagation algorithm until the loss function value converges to obtain the gateway area risk prediction model.

[0052] Optionally, the feature extraction network can employ a Long Short-Term Memory (LSTM) network or a Gated Recurrent Unit (GRU) to capture the non-stationary characteristics of power load as it evolves over time.

[0053] As can be seen, by introducing an attention mechanism to weight and fuse dynamic evolution features and regional parameters through the above optional embodiments, the influence weights of different environmental factors on the operational safety of power nodes can be captured, thereby improving the generalization ability and judgment accuracy of the risk prediction model in complex highway scenarios.

[0054] As an optional embodiment, the above steps, including performing energy consumption structure analysis on the highway based on gateway area risks and identifying abnormal energy consumption data to output operation and management recommendations for power equipment, include: Acquire real-time communication interaction data between each smart gateway and its neighboring smart gateways to construct a communication topology map of the highway power system; Based on the preset correlation analysis algorithm, the propagation and diffusion index of gateway area risk in the communication topology map is calculated, and the historical fault correlation weights corresponding to each smart gateway are retrieved. By combining propagation and diffusion indicators and historical fault association weights, the energy consumption contribution of each node is traced to generate the energy consumption structure analysis results of the highway. Based on the energy consumption structure analysis results, abnormal energy consumption data exceeding the preset fluctuation threshold are identified, and potential fault points of power equipment are mapped by combining historical fault association weights, so as to output corresponding operation and management suggestions.

[0055] Optionally, the correlation analysis algorithm can be based on graph convolutional networks (GCN) or random walk algorithms to analyze the impact of local power failures or energy consumption anomalies on the overall topology.

[0056] As can be seen, through the above optional embodiments, by constructing a communication topology map and introducing historical fault association weights, it is possible to trace the propagation of energy consumption risks among nodes, thereby improving the logical rigor of abnormal energy consumption identification and providing preventive management suggestions for the precise maintenance of power equipment.

[0057] As an optional embodiment, the historical fault association weights in the above steps are determined through the following steps: Obtain all historical fault records of the highway power system within a preset historical period; Extract the set of faulty smart gateways involved in each historical fault record, and count the fault frequency of each smart gateway in the historical fault record; For any two smart gateways, calculate the number of times the two smart gateways co-occur in the same historical fault record; The ratio of co-occurrence frequency to the total failure frequency of each smart gateway in the set of faulty smart gateways is calculated to obtain the primary association weight. The historical fault association weights for each smart gateway are obtained by weighting and summing the primary association weights with the preset fault severity factor.

[0058] Optionally, the severity factor can be set in stages based on the scope of the power outage, the repair time, or the economic losses caused.

[0059] As can be seen, by calculating the co-occurrence ratio of different smart gateways in historical fault records through the above optional embodiments, the degree of fault coupling between nodes can be quantified, thereby improving the logical rigor of power system energy efficiency anomaly tracing and enhancing the prediction accuracy of regional fault chain reactions.

[0060] Specifically, based on the scheme in the embodiments of the present invention, an intelligent communication management gateway (hereinafter referred to as the gateway) and its constituent distributed monitoring system are implemented. A schematic diagram of the gateway's structure is shown below. Figure 4The gateway adopts a 1U standard rack-mount design (266.6mm×483mm×44mm) and can be deployed in power distribution cabinets in highway tunnels, toll stations, monitoring centers, or service areas.

[0061] The specific implementation process is as follows: First, the gateway utilizes its rich set of physical interfaces to collect operational data from power equipment. It is equipped with 16 isolated serial interfaces (including 12 RS485 and 4 RS232), supporting selectable baud rates from 1200bps to 19200bps, and features a comprehensive built-in protocol library. It can connect to various energy meters, relay protection devices, or frequency converters via DLT645 (1997 / 2007 version), Modbus RTU / TCP, IEC60870-5-104, and various PLC protocols (such as Siemens S7 series, Mitsubishi, etc.). Furthermore, the gateway also has 4 DI (wet input) interfaces, enabling real-time monitoring of the switching status or alarm signals of power equipment.

[0062] Secondly, the gateway runs a preset correlation model based on its built-in ARM V8 Cortex-A53 architecture processor (system clock speed up to 1000MHz) and 512MB DDR3 DRAM. Using historical operating data stored in its 8GB eMMC FLASH (and supporting SD card expansion), the gateway performs correlation analysis on energy consumption data such as current, voltage, and power factor collected from different nodes, thereby identifying the corresponding energy consumption correlation characteristics of each gateway.

[0063] Based on the identified correlation features, the gateway uses a predictive model to forecast risks in the gateway area. Because the gateway possesses industrial-grade wide-temperature performance (operating temperature range from -40℃ to 85℃) and its network ports have lightning protection and anti-interference capabilities against 15KV air discharge and 8KV contact discharge, its high reliability is ensured in the complex environment of highways. The area risk data generated by the predictive model can be uploaded to the monitoring center in real time via two 10 / 100 / 1000M adaptive Ethernet ports.

[0064] Finally, the monitoring center or gateway performs energy consumption structure analysis based on the risks in the gateway area. The gateway can identify abnormal energy consumption data (such as excessive line losses, low equipment efficiency, etc.) and output operation and management suggestions for power equipment through its built-in 4-channel relay DO output interface (contact capacity up to 10A 220VAC). For example, when an overload risk is identified in a certain area, the gateway can directly drive the relays to execute emergency load shedding or issue control commands, achieving refined control of energy consumption.

[0065] To ensure continuous system stability, the gateway adopts a dual-power redundant design (PWR1 and PWR2, supporting 90-264V AC input), and the system's full-load power consumption is less than 8W. Combined with natural cooling, this effectively reduces the long-term maintenance costs of the equipment. Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a highway power equipment energy consumption analysis system based on a smart gateway, as disclosed in an embodiment of the present invention. Figure 2 The described smart gateway-based highway power equipment energy consumption analysis system can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the highway power equipment energy consumption analysis system based on a smart gateway may include: The acquisition module 201 is used to acquire power equipment operation data collected by smart gateways deployed at multiple nodes of the highway.

[0066] Optional nodes include tunnels, toll stations, monitoring centers, or service areas.

[0067] The identification module 202 is used to identify the operating energy consumption correlation characteristics of each smart gateway based on a preset association model.

[0068] The prediction module 203 is used to predict the gateway area risk corresponding to each smart gateway based on the prediction model and the correlation characteristics of operating energy consumption.

[0069] The management module 204 is used to perform energy consumption structure analysis on the highway based on the risks of the gateway area and identify abnormal energy consumption data in order to output operation and management suggestions for power equipment.

[0070] As can be seen, the above-mentioned embodiments of the invention acquire power equipment operation data collected by smart gateways deployed at multiple nodes of highways, and use correlation models to identify the correlation characteristics of operating energy consumption. Then, based on prediction models, they determine the risks of gateway areas for energy consumption structure analysis and anomaly identification. This enables digital monitoring and risk warning of the operating status of highway power infrastructure, and provides scientific decision-making suggestions and data support for the precise operation management of power equipment.

[0071] As an optional implementation, the association model is established through the following steps: Acquire operating status data of power equipment within historical time periods and synchronously collect raw energy consumption data; Multi-dimensional aggregation processing is performed on the operating status data and raw energy consumption data to extract the operating condition feature components and energy consumption distribution components of each node under different operating conditions. Calculate the correlation coefficient between each operating condition characteristic component and the corresponding energy consumption distribution component; Based on the correlation coefficient, a mapping function between operating status and energy consumption level is established as a correlation model.

[0072] As can be seen, through the above optional embodiments, by performing multi-dimensional aggregation and correlation analysis on historical operating data and energy consumption data, a precise mapping relationship between equipment operating conditions and energy consumption can be established, thereby providing a quantitative calculation model for subsequent energy consumption correlation feature extraction and enhancing the system's ability to perceive the energy consumption fluctuation patterns of power equipment.

[0073] As an optional embodiment, the identification module identifies the specific method by which it identifies the operational energy consumption correlation characteristics corresponding to each smart gateway based on a preset association model, including: Identify the operating status identifiers and synchronous power acquisition characteristics of each smart gateway-connected device from the power equipment operation data; The operating condition identifier and power collection characteristics are input into the correlation model to match the energy consumption response benchmark of each downstream device in different time windows; Calculate the energy consumption offset vector of the energy acquisition characteristics relative to the energy consumption response benchmark; The energy consumption offset vectors corresponding to multiple downstream devices are aggregated at the gateway level to generate the operating energy consumption correlation features for each smart gateway.

[0074] As can be seen, through the above optional embodiments, by matching the energy consumption response benchmark of the downstream equipment and the vector aggregation at the gateway dimension, it is possible to extract the correlation features that reflect the power operation pattern of the node, thereby improving the detection accuracy of abnormal power fluctuations on highways.

[0075] As an optional embodiment, the specific method by which the identification module calculates the energy consumption offset vector of the energy collection characteristics relative to the energy consumption response benchmark includes: The power acquisition features are input into a preset vectorization network algorithm to generate acquisition feature vectors in a high-dimensional feature space. The energy consumption response benchmark is embedded using a vectorized network algorithm to obtain the corresponding benchmark reference vector; Based on a preset vector distance algorithm, the spatial positional differences between the collected feature vector and the benchmark reference vector in each dimension are calculated. The direction and magnitude are encoded based on spatial location differences to generate an energy consumption offset vector that reflects the amplitude of power fluctuations.

[0076] As can be seen, through the above optional embodiments, by extracting high-dimensional features through vectorized network algorithms and combining them with vector distance algorithms to calculate spatial differences, it is possible to accurately quantify the subtle deviations between real-time collected features and the benchmark, thereby effectively improving the accuracy of describing and the sensitivity of identifying abnormal fluctuations in energy consumption under complex environments.

[0077] As an optional embodiment, the prediction module, based on a prediction model and according to the correlation characteristics of operating energy consumption, predicts the specific method by which it predicts the gateway area risk corresponding to each smart gateway, including: Obtain historical communication data for each smart gateway and regional parameters of the smart gateway's deployment location; Message statistical analysis is performed on historical communication data to extract communication stability feature components that reflect the communication quality of the smart gateway. The operating energy consumption correlation features, communication stability feature components and regional parameters are subjected to multi-dimensional feature fusion processing to generate a comprehensive evaluation feature vector for each smart gateway. The comprehensive assessment feature vector is input into the preset risk prediction model. The risk prediction model maps the comprehensive assessment feature vector to risk levels to predict the gateway area risk corresponding to each smart gateway.

[0078] As can be seen, through the above optional embodiments, the correlation mapping between energy consumption anomalies and communication fluctuations is realized by integrating regional parameters and historical communication data, thereby improving the reliability of predicting the operational risks of highway power nodes.

[0079] As an optional implementation, the risk prediction model is trained through the following steps: Obtain multiple sample datasets of the power system of the highway during its historical operating cycle; optionally, each sample dataset includes historical operating energy consumption correlation features, historical communication stability feature components, historical regional parameters, and corresponding measured risk level labels; The historical energy consumption correlation features and historical communication stability features are input into a preset feature extraction network to extract the dynamic evolution features of different nodes over time. Based on the attention mechanism, dynamic evolution features and historical region parameters are weighted and fused to obtain a multi-dimensional fused feature vector corresponding to each sample dataset. The multidimensional fused feature vector is input into the risk prediction network to be trained for forward propagation to output the predicted risk result; The loss function value between the predicted risk result and the measured risk level label is calculated, and the weight parameters of the risk prediction network are updated based on the backpropagation algorithm until the loss function value converges to obtain the gateway area risk prediction model.

[0080] As can be seen, by introducing an attention mechanism to weight and fuse dynamic evolution features and regional parameters through the above optional embodiments, the influence weights of different environmental factors on the operational safety of power nodes can be captured, thereby improving the generalization ability and judgment accuracy of the risk prediction model in complex highway scenarios.

[0081] As an optional embodiment, the management module performs energy consumption structure analysis on the highway based on gateway area risks and identifies abnormal energy consumption data, in order to output specific methods for operational management recommendations for power equipment, including: Acquire real-time communication interaction data between each smart gateway and its neighboring smart gateways to construct a communication topology map of the highway power system; Based on the preset correlation analysis algorithm, the propagation and diffusion index of gateway area risk in the communication topology map is calculated, and the historical fault correlation weights corresponding to each smart gateway are retrieved. By combining propagation and diffusion indicators and historical fault association weights, the energy consumption contribution of each node is traced to generate the energy consumption structure analysis results of the highway. Based on the energy consumption structure analysis results, abnormal energy consumption data exceeding the preset fluctuation threshold are identified, and potential fault points of power equipment are mapped by combining historical fault association weights, so as to output corresponding operation and management suggestions.

[0082] As can be seen, through the above optional embodiments, by constructing a communication topology map and introducing historical fault association weights, it is possible to trace the propagation of energy consumption risks among nodes, thereby improving the logical rigor of abnormal energy consumption identification and providing preventive management suggestions for the precise maintenance of power equipment.

[0083] As an optional implementation, the historical fault association weights are determined through the following steps: Obtain all historical fault records of the highway power system within a preset historical period; Extract the set of faulty smart gateways involved in each historical fault record, and count the fault frequency of each smart gateway in the historical fault record; For any two smart gateways, calculate the number of times the two smart gateways co-occur in the same historical fault record; The ratio of co-occurrence frequency to the total failure frequency of each smart gateway in the set of faulty smart gateways is calculated to obtain the primary association weight. The historical fault association weights for each smart gateway are obtained by weighting and summing the primary association weights with the preset fault severity factor.

[0084] As can be seen, by calculating the co-occurrence ratio of different smart gateways in historical fault records through the above optional embodiments, the degree of fault coupling between nodes can be quantified, thereby improving the logical rigor of power system energy efficiency anomaly tracing and enhancing the prediction accuracy of regional fault chain reactions.

[0085] Example 3 Please see Figure 3 , Figure 3 This is another energy consumption analysis system for highway power equipment based on a smart gateway disclosed in the embodiments of the present invention. Figure 3 The described smart gateway-based highway power equipment energy consumption analysis system is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the highway power equipment energy consumption analysis system based on a smart gateway may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the energy consumption analysis method for highway power equipment based on a smart gateway as described in Embodiment 1.

[0086] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the energy consumption analysis method for highway power equipment based on a smart gateway as described in Embodiment 1.

[0087] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the energy consumption analysis method for highway power equipment based on a smart gateway described in Embodiment 1.

[0088] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0090] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0091] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0097] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0099] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0100] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0101] Finally, it should be noted that the energy consumption analysis method and system for highway power equipment based on a smart gateway disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A highway power equipment energy consumption analysis method based on an intelligent gateway, characterized in that, The method comprises: acquiring power equipment operation data collected by intelligent gateways deployed at multiple nodes of the expressway; the nodes are tunnels, toll stations, monitoring centers or service areas; based on a preset correlation model, identifying operation energy consumption correlation characteristics corresponding to each intelligent gateway; based on a prediction model, predicting gateway area risks corresponding to each intelligent gateway according to the operation energy consumption correlation characteristics; based on the gateway area risks, performing energy consumption structure analysis on the expressway and identifying abnormal energy consumption data to output operation management suggestions for the power equipment. 2.The smart gateway based highway power equipment energy consumption analysis method of claim 1, wherein, The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. 3.The smart gateway based highway power equipment energy consumption analysis method of claim 2, wherein, The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. 4.The smart gateway based highway power equipment energy consumption analysis method of claim 3, wherein, The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. 5.The smart gateway based highway power equipment energy consumption analysis method of claim 1, wherein, The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy consumption data to extract working condition characteristic components and energy consumption distribution components of each node under different working conditions; calculating correlation coefficients between each working condition characteristic component and the corresponding energy consumption distribution component; based on the correlation coefficients, establishing a mapping function between operation state and energy consumption level as the correlation model. The correlation model is established by the following steps: acquiring operation state data and synchronously collected original energy consumption data of the power equipment in a historical period; performing multi-dimensional aggregation processing on the operation state data and the original energy The comprehensive evaluation feature vector is input into a preset risk prediction model, and the risk prediction model is used for risk level mapping of the comprehensive evaluation feature vector, so as to predict a gateway area risk corresponding to each intelligent gateway. 6.The smart gateway based highway power device energy consumption analysis method of claim 5, wherein, The risk prediction model is obtained by the following steps: Obtain a plurality of sample data sets of the power system of the expressway in a historical operation cycle; each sample data set comprises historical operation energy consumption correlation features, historical communication stability feature components, historical area parameters, and a corresponding measured risk level label; The historical operation energy consumption correlation features and the historical communication stability feature components are input into a preset feature extraction network to extract dynamic evolution features of different nodes in a time sequence; Based on an attention mechanism, the dynamic evolution features and the historical area parameters are weighted and fused to obtain a multi-dimensional fusion feature vector corresponding to each sample data set; The multi-dimensional fusion feature vector is input into a risk prediction network to be trained for forward propagation, so as to output a prediction risk result; A loss function value between the prediction risk result and the measured risk level label is calculated, and the weight parameters of the risk prediction network are updated based on a back propagation algorithm until the loss function value converges to obtain the gateway area risk prediction model. 7.The smart gateway based highway power equipment energy consumption analysis method of claim 1, wherein, According to the gateway area risk, the expressway is subjected to energy consumption structure analysis and abnormal energy consumption data are identified to output operation management suggestions for power equipment, comprising: Obtain real-time communication interaction data between each intelligent gateway and its adjacent intelligent gateway to construct a communication topology map of the expressway power system; Based on a preset correlation analysis algorithm, a propagation and diffusion index of the gateway area risk in the communication topology map is calculated, and a historical fault correlation weight corresponding to each intelligent gateway is called; Based on the propagation and diffusion index and the historical fault correlation weight, the energy consumption contribution degree of each node is traced to generate an energy consumption structure analysis result of the expressway; According to the energy consumption structure analysis result, abnormal energy consumption data exceeding a preset fluctuation threshold are identified, and potential fault points of power equipment are mapped based on the historical fault correlation weight to output corresponding operation management suggestions. 8.The smart gateway based highway power device energy consumption analysis method of claim 7, wherein, The historical fault correlation weight is determined by the following steps: Obtain full historical fault records of the expressway power system in a preset historical period; Extract a set of fault intelligent gateways involved in each historical fault record, and count the fault frequency of each intelligent gateway in the historical fault record; For any two intelligent gateways, the co-occurrence number of the two intelligent gateways appearing in the same historical fault record is calculated; A record ratio between the co-occurrence number and the total fault frequency of each intelligent gateway in the set of fault intelligent gateways is calculated to obtain a primary correlation weight; The primary correlation weight and a preset fault severity factor are weighted and summed to obtain a historical fault correlation weight corresponding to each intelligent gateway.

9. A highway power equipment energy consumption analysis system based on an intelligent gateway, characterized in that, The system comprises: An acquisition module is configured to acquire power equipment operation data collected by intelligent gateways deployed at multiple nodes of an expressway; the nodes are tunnels, toll stations, monitoring centers, or service areas; An identification module is configured to identify, based on a preset correlation model, an operation energy consumption correlation feature corresponding to each intelligent gateway; A prediction module is configured to predict, based on a prediction model, a gateway area risk corresponding to each intelligent gateway according to the operation energy consumption correlation feature; A management module is configured to perform energy consumption structure analysis on the expressway and identify abnormal energy consumption data according to the gateway area risk, and output an operation management suggestion for power equipment.

10. A highway power equipment energy consumption analysis system based on an intelligent gateway, characterized in that, The system comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the intelligent gateway-based expressway power equipment energy consumption analysis method according to any one of claims 1-8.

Images