Highway load side dynamic monitoring method, system, equipment and medium

Abstract

The invention provides an expressway load side dynamic monitoring method, system and device and a medium, and belongs to the technical field of expressways, and the method comprises the steps: constructing an Internet of Things sensing network, and collecting an electrical load index in real time; performing space-time alignment on the electrical load indexes through an edge computing gateway, and generating a standardized data set by adopting a sliding window mechanism; constructing a three-dimensional feature space; establishing a causal chain model, and determining a coupling strength coefficient of an equipment start-stop threshold value and a peripheral load; defining and dividing a core guarantee load, an important guarantee load and an adjustable load, constructing a multi-objective optimization function, and adopting model prediction control to perform rolling optimization on the position of a main transformer tap and a reactive power compensation device switching combination; and comparing the calculation result with a preset target value, and evaluating the dynamic monitoring state of the highway load side. The method solves the problem that load management lacks pertinence, meets different requirements of different loads for power supply, and improves the overall operation efficiency of a power system.

Description

Technical Field

[0001] The present invention belongs to the technical field of expressways, and in particular relates to a method, system, equipment and medium for dynamic monitoring of the load side of an expressway. Background Art

[0002] As the number of cars increases, highway traffic volume continues to rise. To better manage traffic flow, highways are equipped with a variety of monitoring technologies. This requires a better power supply to meet the load requirements.

[0003] In relevant highway load-side monitoring, the focus is often only on the collection of some key power parameters, such as the active power of the distribution cabinet, while ignoring other important indicators such as reactive power, apparent power, cable temperature, lighting brightness, and charging pile load rate. This makes it difficult to meet the needs of accurate monitoring of complex highway power supply systems.

[0004] Related methods have limited research on the temporal correlations between loads, with most relying on empirical, qualitative judgments and lacking scientific, systematic analytical tools. The causal relationships between equipment loads during conditions such as tunnel ventilation unit startup and lighting system downshifting are unclear, making it difficult to accurately determine equipment start / stop thresholds and the coupling strength coefficients of surrounding loads. This makes it difficult to rationally control the interactions between equipment in actual operation, potentially leading to unstable power system operation.

[0005] Existing technologies do not formulate differentiated power supply strategies for core power-maintaining loads, important guarantee loads and adjustable loads, and cannot meet the different requirements of various loads for power supply reliability, stability and power quality. This may cause core businesses to be affected by power supply problems. At the same time, the potential of adjustable loads has not been fully tapped, reducing the overall operating efficiency of the power system. Summary of the Invention

[0006] The present invention provides a method for dynamic monitoring of the load side of a highway, which solves the problem of lack of pertinence in load management, meets the different power supply requirements of different loads, and improves the overall operating efficiency of the power system.

[0007] Methods include: S101: Build an IoT sensing network to collect electrical load indicators in real time; S102: Use the edge computing gateway to perform spatiotemporal alignment of electrical load indicators and generate a standardized data set using a sliding window mechanism; S103: Perform cluster analysis on electrical load indicators, construct a three-dimensional feature space, and set a silhouette coefficient threshold to achieve pattern recognition of traffic guidance screens, communication base stations, and variable information boards; S104: Analyze the temporal correlation between loads, establish a causal chain model for the start-up of tunnel ventilation units and the downshifting of lighting systems, and determine the coupling strength coefficient between the equipment start-up and shutdown thresholds and the surrounding loads; S105: Define and classify core power loads, important power loads, and adjustable loads based on the coupling strength coefficient, and set differentiated QoS parameters; S106: Construct a multi-objective optimization function, combine it with Monte Carlo simulation to predict the load trend for a preset time in the future, and use model predictive control to optimize the main transformer tap position and the switching combination of reactive power compensation devices in a rolling manner; S107: Based on the load trend, obtain the real-time operating parameters of each electrical device, calculate the average value and fluctuation range of each indicator in different time periods based on the preset evaluation indicators, compare the calculation results with the preset target values, and evaluate the dynamic monitoring status of the highway load side.

[0008] Preferably, step S103 specifically includes: Preprocessing electrical load index data; Construct a three-dimensional feature space based on power factor, active / reactive ratio, and daily load curve similarity; The DTW algorithm is used to calculate the similarity of daily load curves, and the relevant data of each electrical device is mapped into the three-dimensional feature space to form corresponding feature points; Select a clustering algorithm to perform cluster analysis on feature points in the three-dimensional feature space; The optimal K value is determined by combining the elbow rule, and K cluster centers are randomly initialized. Each feature point is assigned to the closest cluster according to the distance between the feature point and the cluster center. The center of each cluster is recalculated, and the distribution of cluster centers and feature points is continuously updated iteratively until the clustering results converge and the silhouette coefficient threshold is obtained.

[0009] Preferably, step S105 specifically includes: evaluating the impact intensity between devices by the power change correlation when the devices are started and stopped; Among them, a dynamic correlation matrix is ​​established to record the power fluctuation impact of the start-stop operation load of different equipment, and the time series correlation of power changes is analyzed using the cross-correlation function. Combined with the physical connection relationship between the equipment, the correlation weight of the core equipment and auxiliary equipment is determined; Divide load levels based on the dual standards of coupling strength coefficient and equipment importance; Set differentiated power supply guarantee strategies for different levels of loads; Establish an adaptive adjustment system based on real-time monitoring data, triggering the recalculation of grading standards when equipment aging or operating condition changes are detected; combine Monte Carlo simulation to predict future load trends and dynamically optimize QoS parameter thresholds; When voltage exceeds the limit or feeder is overloaded, the hierarchical strategy upgrade is automatically triggered.

[0010] Preferably, step S101 further comprises: deploying an intelligent sensor device with blockchain node function in the highway power supply and distribution system, synchronously generating a digital certificate with a timestamp when collecting electrical load indicators such as power parameters of distribution cabinets, cable current carrying capacity, and tunnel lighting brightness, and constructing a decentralized sensing network through a star topology structure; The original electrical data is dynamically compressed and encoded using a preset algorithm, and data blocks are generated according to a preset time period. Each block contains a triple check code of the preceding hash value, timestamp, and device fingerprint; Establish a three-level verification system consisting of roadside units, regional controllers, and cloud verification nodes, and use the national secret SM3 algorithm to implement transmission data; Model watermarking technology is introduced during the load feature extraction phase. Device registration information and algorithm version numbers are compiled into implicit watermarks and embedded into the clustering model. When the k-means++ algorithm generates a three-dimensional feature space, a traceable digital watermark is automatically embedded. A load-grading execution framework is built based on a private chain, and the load control strategy is compiled into a smart contract, which is automatically triggered when a voltage sag occurs.

[0011] Preferably, step S107 further comprises: using a dynamic compression coding algorithm to compress the real-time operating parameters of each electrical device in real time, and adding a timestamp and a data fingerprint; Analyze load characteristics based on continuity and periodicity indicators and calculate adjustments to optimize encoding parameters; Dynamically adjust the coding table according to changes in data characteristics; Combining national standard classification criteria with predictive factors, dynamically divide load levels and generate multi-objective optimization power supply strategies; Verify the effectiveness of control instructions through the digital twin platform, triggering the adaptive correction mechanism to adjust the reactive power compensation device; Perform secondary compression storage on the total data sequence based on the update frequency to reduce cloud storage overhead; System security is ensured through encrypted logging and parameter self-calibration, and coding and classification thresholds are calibrated regularly.

[0012] Preferably, the step of dynamically adjusting the coding table according to changes in data characteristics specifically includes: If the adjustment possibility W of a load pattern is greater than 0.2 and the updating degree is significant, the updating degree calculation formula is:

[0013] Among them, n is the number of times the load pattern occurs in the current cycle, a is the current total load, is the number of historical occurrences, is the total amount of historical data; The load levels are divided into: A, B, and C, and the classification thresholds are adjusted based on dynamic data characteristics; The dynamic power supply strategy is generated by predictive control, and the optimization objective function is:

[0014] in, is the power loss of cables and transformers, λ1 is the voltage deviation weight coefficient, ΔU is the difference between the actual voltage and the rated voltage, λ2 is the frequency deviation weight coefficient, which is used to adjust the weight coefficient of the frequency deviation (|f − f0|) on the objective function; f is the actual grid frequency, f0 is the rated grid frequency; λ3 is the adjustment possibility weight coefficient.

[0015] Preferably, step S106 further includes: The multi-protocol parsing engine collects and identifies protocol data from heterogeneous devices in the power supply and distribution system, stores it in a buffer, and performs timing preprocessing. Select compression algorithm based on data type and dynamically optimize compression parameters; Deploy the selected compression algorithm to compress the data, attach a timestamp and data fingerprint, and then transmit it to the cloud; Dynamically adjust the compression strategy of load levels and generate multi-objective optimization power supply strategies; Use segmented storage and dynamic indexing technology to store compressed data, decode segment by segment through preset coding tables and splice incomplete data segments; Configure the digital twin platform to verify control instructions, trigger the adaptive mechanism to adjust the reactive compensation device and compression parameters, and periodically calibrate the encoding rules to adapt to data pattern changes.

[0016] The present application also provides a highway load-side dynamic monitoring system, the system comprising: The data acquisition module is used to build an IoT sensing network covering a preset section of the highway and collect electrical load indicators in real time; The indicator generation module is used to align electrical load indicators in time and space through the edge computing gateway, and uses a sliding window mechanism to generate a standardized data set containing instantaneous power, load fluctuation rate, and harmonic distortion rate; The analysis and processing module is used to perform cluster analysis on electrical load indicators, construct a three-dimensional feature space based on power factor, active / reactive power ratio, and daily load curve similarity, and set the contour coefficient threshold to achieve pattern recognition of traffic guidance screens, communication base stations, and variable information boards; The load analysis module is used to analyze the temporal correlation between loads, establish a causal chain model for the start-up of tunnel ventilation units and the downshifting of lighting systems, and determine the coupling strength coefficient between the equipment start-up and shutdown thresholds and the surrounding loads; The parameter processing module is used to define and divide the core power load, important guarantee load, and adjustable load using the coupling strength coefficient, and set differentiated QoS parameters; The load analysis module uses core power-maintaining loads, important guarantee loads, and adjustable loads to construct a multi-objective optimization function. This module uses Monte Carlo simulation to predict future load trends for a preset time period and employs model predictive control to optimize the main transformer tap position and reactive compensation device switching combinations. The evaluation and monitoring module is used to use the load trend to obtain the real-time operating parameters of each electrical equipment. Based on the preset evaluation indicators, it calculates the average value and fluctuation range of each indicator in different time periods, compares the calculation results with the preset target values, and evaluates the dynamic monitoring status of the highway load side.

[0017] According to another embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the highway load side dynamic monitoring method when executing the program.

[0018] According to another embodiment of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the highway load side dynamic monitoring method are implemented.

[0019] It can be seen from the above technical solutions that the present invention has the following advantages: The dynamic monitoring method for highway loads provided in this application deploys multiple types of smart sensors to build an IoT sensing network, collects various electrical load indicators, and utilizes an edge computing gateway for spatiotemporal alignment and standardized data set generation. This method addresses the issues of incomplete and inaccurate data collection. Cluster analysis is used to construct a three-dimensional feature space and set silhouette coefficient thresholds for pattern recognition. Load characteristics are mined to accurately identify the power usage patterns of different devices. A preset algorithm is used to mine temporal correlations between loads and establish a causal chain model. Load correlations are clarified, and device start / stop thresholds and coupling strength coefficients are determined. This effectively improves power system operational stability and mitigates issues such as voltage fluctuations and frequency anomalies. Loads are graded based on coupling strength coefficients and importance, and differentiated QoS parameters are set. This addresses the lack of targeted load management, meets the diverse power supply requirements of different loads, and improves the overall operational efficiency of the power system. A multi-objective optimization function is constructed, combining simulation prediction with model predictive control. This enables accurate prediction of future load trends and dynamic optimization control of the power system. This reduces system power loss, maintains voltage and frequency stability, and improves power supply quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of the dynamic monitoring method for the load side of a highway; Figure 2 This is a schematic diagram of the dynamic monitoring system on the load side of the expressway; Figure 3 Schematic diagram of an electronic device. DETAILED DESCRIPTION

[0022] Various embodiments of the highway load-side dynamic monitoring method will be described more fully below. The present disclosure is capable of various embodiments, and modifications and variations may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein. Instead, the present disclosure is to be construed as encompassing all modifications, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of the present disclosure.

[0023] In the highway load-side dynamic monitoring method, the terms "including" or "may include" as used in various embodiments of the present disclosure indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "including," "having," and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be understood as excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing.

[0024] The term “user” used in various embodiments of the present disclosure may indicate a person using an electronic device or a device using the electronic device.

[0025] The terms used in the various embodiments of the present disclosure are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise specified, all terms used herein (including technical terms and scientific terms) have the same meaning as those generally understood by those skilled in the art to which the various embodiments of the present disclosure belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.

[0026] 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.

[0027] See also Figure 1 FIG2 is a flow chart of a method for dynamic monitoring of the load side of a highway in a specific embodiment, the method comprising: Step S101: Smart meters, voltage and current transformers, temperature sensors, and environmental sensing terminals are deployed in the highway power supply and distribution system to build an IoT sensing network covering a preset section of the highway to collect electrical load indicators in real time; electrical load indicators include: distribution cabinet power parameters, cable temperature, tunnel lighting brightness, and charging pile load rate.

[0028] In highway power supply and distribution systems, appropriate smart meters, voltage and current transformers, temperature sensors, and environmental sensing terminals are selected based on different monitoring requirements. Smart meters accurately measure the power parameters of the distribution cabinet. Voltage and current transformers are selected based on the voltage level and current range of the distribution cabinet to ensure accurate voltage and current measurement. Temperature sensors are deployed at key cable locations, such as cable joints, to monitor cable temperature in real time. Environmental sensing terminals are installed in tunnels and near charging stations to monitor lighting brightness and charging station load.

[0029] The above devices are connected through wired or wireless communication to build a connected sensing network. The smart meter collects real-time active power, reactive power, apparent power and other parameters of the power distribution cabinet; the voltage current transformer converts high voltage and large current into small signals suitable for measurement and transmits them to the monitoring device; the temperature sensor senses the temperature change of the cable through a thermosensitive element and converts it into an electrical signal for transmission; the environmental perception terminal measures the lighting brightness using a photosensitive element and monitors the load rate through the internal circuit of the charging pile. All collected data is transmitted in real time to the edge computing gateway through the network.

[0030] Step S102: Spatiotemporal alignment of electrical load indicators is performed by the edge computing gateway, and a standardized data set containing instantaneous power, load fluctuation rate, and harmonic distortion rate is generated using a sliding window mechanism.

[0031] In some embodiments, the edge computing gateway receives electrical load indicator data from different devices. Due to slight differences in the data collection time of each device, spatiotemporal alignment is required. According to the geographical location information and time stamp of the device, a time synchronization algorithm is used to calibrate the data in time, ensuring that the data collected by different devices at the same time can be correctly associated.

[0032] This embodiment sets a fixed length sliding window, for example, 10 minutes. Within the window, the collected electrical load indicator data is calculated and processed to generate a standardized data set containing instantaneous power, load fluctuation rate, and harmonic distortion rate.

[0033] Instantaneous power is obtained by multiplying the instantaneous values of voltage and current; load fluctuation rate is obtained by calculating the power change rate within the window; and harmonic distortion rate is calculated by performing Fourier transform on the voltage and current signals to analyze the harmonic content. The window continuously slides with time, continuously generating new standardized data sets.

[0034] It can be understood that the NTP protocol transmits time information through the network, and the devices synchronize with the time server to ensure that the times of the devices are consistent. Based on the time series data processing principle, the data is statistically analyzed and feature extracted within a fixed time window. The sliding window continuously moves to realize dynamic analysis of continuous time series data.

[0035] Step S103: Cluster analysis is performed on the electrical load indicators to construct a three-dimensional feature space based on power factor, active / reactive power ratio, and daily load curve similarity, and a contour coefficient threshold is set to realize mode recognition of traffic guidance screens, communication base stations, and variable information boards.

[0036] In some embodiments, the following steps are specifically included: Step S1031: Preprocess the electrical load metrics collected through the IoT sensing network and processed by the edge computing gateway. This preprocessing can involve identifying and addressing missing values, and interpolation can be used to supplement missing electrical load metrics. Then, the electrical load metrics are standardized, normalizing data such as power factor, active / reactive power ratio, and daily load curves to eliminate the impact of different metric dimensions and numerical ranges, making the different metrics comparable.

[0037] Step S1032: construct a three-dimensional feature space based on the three key features of power factor, active to reactive ratio, and daily load curve similarity.

[0038] The power factor reflects the efficiency of electrical equipment in utilizing electrical energy, the active-to-reactive ratio reflects the equipment's power usage characteristics, and the daily load curve similarity reflects the degree of similarity in the equipment's power usage patterns throughout the day. A dynamic time warping algorithm can be used to calculate daily load curve similarity, allowing the daily load curves of different equipment to be compared under a unified standard. The relevant data for each electrical device is mapped into this three-dimensional feature space, forming corresponding feature points.

[0039] Step S1033: Use the K-means algorithm to perform cluster analysis on the feature points in the three-dimensional feature space. Before clustering, determine the number of clusters, K. The optimal K value can be determined through multiple experiments combined with the elbow rule. The elbow rule calculates the clustering error for different K values, and the sum of squared errors gradually decreases. When the K value reaches a certain point, the rate of decrease in the sum of squared errors slows significantly. The K value corresponding to this point is the optimal value.

[0040] K cluster centers are randomly initialized, and each feature point is assigned to the closest cluster based on the distance between the feature point and the cluster center. Then, the center of each cluster is recalculated, and the assignment of cluster centers and feature points is iteratively updated until the clustering results converge.

[0041] Step S1034: Based on the clustering results, analyze the electrical equipment in each cluster to identify the power usage patterns of typical equipment such as traffic guidance screens, communication base stations, and variable information boards. A silhouette coefficient threshold is set. The silhouette coefficient measures the closeness of each sample point to its cluster and its separation from other clusters.

[0042] For each sample point, its silhouette coefficient is calculated. The closer the silhouette coefficient is to 1, the more similar the sample point is to its cluster and the better its separation from other clusters. By setting an appropriate silhouette coefficient threshold, sample points that match typical equipment power usage patterns are screened, enabling accurate pattern recognition for equipment such as traffic guidance screens, communication base stations, and variable information boards.

[0043] Based on the clustering results, the characteristics of the data points in each cluster are analyzed and a silhouette coefficient threshold is set. The silhouette coefficient measures the closeness of a data point to its cluster and its degree of separation from other clusters. By comparing the silhouette coefficient of each data point with the threshold, the power usage patterns of equipment such as traffic guidance screens, communication base stations, and variable information boards can be identified.

[0044] Step S104: Use the FP-Growth algorithm to mine the temporal correlation between loads, establish a causal chain model under the conditions of tunnel ventilation unit startup and lighting system downshifting, and determine the coupling strength coefficient between the equipment start-stop threshold and the surrounding loads.

[0045] In some embodiments, the data after cluster analysis and pattern recognition is further organized into a transaction data set suitable for processing by the FP-Growth algorithm. Each transaction represents the power usage status of different devices within a time period, such as device startup and shutdown. The FP-Growth algorithm was used to mine transaction data sets. This algorithm rapidly uncovers temporal correlations between loads by constructing a frequent pattern tree. For example, a frequent pattern of lighting system downshifting after the tunnel ventilation unit was started was discovered. Based on the discovered correlations, a causal chain model was established. Equipment start / stop thresholds—those thresholds for load-related parameters at which equipment starts or stops—were determined. By analyzing the mutual impact of load changes on different equipment within the correlations, the coupling strength coefficients of surrounding loads were calculated, quantifying the interactions between equipment.

[0046] Step S105: Based on the coupling strength coefficient, define and classify the core power supply load, important guarantee load, and adjustable load, and set differentiated QoS parameters. Among them, the core power supply load is Class A, the important guarantee load is Class B, and the adjustable load is Class C. Differentiated QoS parameters are set.

[0047] It should be noted that for Class A load: MTBF ≥ 10^6 hours, switching delay < 10ms.

[0048] Class B load: 5% amplitude fluctuation is allowed, and the response time is ≤5s.

[0049] Class C load: peak shaving and valley filling depth > 30%.

[0050] In some embodiments, loads are graded based on their importance to highway operations and their coupling with the power system, taking into account safety, functionality, and other factors. Based on the characteristics and requirements of different load levels, combined with power system operating standards and practical experience, corresponding service quality parameters are set to meet the power supply requirements of different loads.

[0051] It should be noted that the various load types are analyzed based on the coupling strength coefficients determined in step S104. Loads that are critical to the safe operation of the highway and have a high coupling strength with other loads are defined as core power-maintenance loads (Class A), such as traffic monitoring systems and emergency communication equipment. Loads that are important to operations and have a moderate coupling strength are defined as critical support loads (Class B), such as some communication base stations and major road lighting facilities. Loads that have low requirements for power continuity and a weak coupling strength are defined as adjustable loads (Class C), such as some non-critical area lighting and charging stations during certain hours.

[0052] Step S106: Based on the core power supply load, important guarantee load, and adjustable load, a multi-objective optimization function is constructed. Combined with Monte Carlo simulation, the load trend for a preset time period in the future is predicted. Model predictive control is used to optimize the main transformer tap position and the switching combination of the reactive power compensation device in a rolling manner.

[0053] In some embodiments, a multi-objective optimization function is constructed, taking into account multiple objectives, such as system power loss, voltage stability, and frequency stability. Monte Carlo simulation is used to generate a large number of possible future load scenarios based on historical load data and influencing factors (such as time and weather). By analyzing these scenarios, load trends are predicted for a preset time period (e.g., two hours).

[0054] Using the MPC model predictive control method, we continuously optimize the main transformer tap position and reactive power compensation device switching combination based on predicted load trends and a multi-objective optimization function. Within each control cycle, we calculate the optimal control strategy, implement it, and then perform the next round of optimization based on new load data.

[0055] As can be seen, this embodiment transforms the problem into a single-objective optimization problem by performing a weighted summation of multiple objective functions. This approach seeks the optimal overall solution while satisfying the various objectives. Based on the principles of probability and statistics, a large number of random simulations are used to generate possible load scenarios. Simulation parameters are then determined using historical data and statistical laws to predict load trends. Future states are predicted based on the system model, and a rolling optimization control strategy is implemented to optimize system performance within each control cycle, while also considering system constraints.

[0056] Step S107: Based on the load trend, obtain the real-time operating parameters of each electrical equipment, calculate the average value and fluctuation range of each indicator in different time periods based on the preset evaluation indicators, compare the calculation results with the preset target values, and evaluate the dynamic monitoring status of the highway load side.

[0057] In some embodiments, a series of evaluation indicators are determined, such as system power balance (the degree of match between actual total power generation and total load), power supply reliability for each load level (statistical analysis of the number and duration of power outages at each load level), and voltage compliance rate (the percentage of time the bus voltage is within the standard range). Operating parameters of each electrical device, such as power, voltage, and current, are collected in real time. Based on the collected data, statistical quantities such as the average value and fluctuation range of each evaluation indicator over different time periods are calculated. The calculated results are compared with preset target values ​​to determine the health of the dynamic monitoring status of the highway load side. If certain indicators do not meet the standards, the reasons are analyzed, such as equipment aging and unreasonable control strategies.

[0058] Thus, this embodiment determines evaluation indicators based on power system operating requirements and highway load characteristics, focusing on safety, reliability, and stability to reflect system operating status. Statistical methods are used to process and analyze collected data, and system performance is evaluated by comparing it with target values. Feedback is then used to guide system optimization.

[0059] In some specific examples, a mountain highway tunnel complex (total length 15km) includes three tunnels, two service areas, and a total load of 5MW. This method is deployed to achieve intelligent control. The specific steps for implementation are: S101: Light sensors (TSL2591) are deployed every 50 meters in the tunnel, and fiber optic temperature sensors (OSEN-FBG-01) are installed at cable connectors. Charging stations in the service area are equipped with smart meters (HIOKI PW3390) with a sampling rate of 1kHz.

[0060] S102: The edge gateway (Huawei Atlas 500) performs spatiotemporal alignment and dynamically adjusts the sliding window width (5 minutes in steady state and 1 minute in transient state).

[0061] S103: Clustering identifies three types of loads: Class A: emergency lighting (profile factor 0.72); Class B: ventilation unit (profile coefficient 0.65); Class C: billboard (silhouette coefficient 0.58); S104: Mined rule: The lighting power drops by 20% within 5 minutes after the ventilation unit is started (confidence level 82%).

[0062] S105: Set the load response time of Class A to <10ms, Class B to allow voltage fluctuations of ±5%, and Class C to participate in peak and valley electricity price response.

[0063] S106: Monte Carlo predicts a 30% increase in evening peak load, and the MPC controls the reactive power compensation device to operate with two sets of capacitors.

[0064] S107: The evaluation shows that THD is reduced from 6.8% to 4.2%, and the monthly average failure time is reduced from 5.2 hours to 0.7 hours.

[0065] It can be seen that the comprehensive line loss rate is reduced from 8.3% to 6.1%, and the MTBF is increased from 1.2x10^5 hours to 9.5x10^5 hours.

[0066] Based on this, the load level is divided, the core power protection load adopts double power supply, and the MTBF and switching delay meet the requirements; the adjustable load (such as part of the service area lighting during off-peak hours) is controlled to fill the valley. Through multi-objective optimization and model predictive control, the main transformer tap position and reactive power compensation device switching are adjusted. After a period of operation, the evaluation index shows that the system power balance degree is improved, and the voltage qualified rate is increased from 80% to 95%, verifying the effectiveness of the method.

[0067] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully describe the specific implementation process in this embodiment, the method comprises: Step S301: An intelligent sensing device with a blockchain node function is arranged in the expressway power supply system, the device integrates a quantum encryption module and a lightweight consensus algorithm, and when collecting electrical load indicators such as power parameters of power distribution cabinets, cable carrying capacity, and tunnel lighting brightness, a digital certificate with a time stamp is generated synchronously, and a decentralized perception network is constructed through a star topology.

[0068] Step S302: The original electrical data is dynamically compressed and encoded by using an improved LZ4 algorithm, data blocks are generated at a 5-minute period, each block contains a triple check code of a previous hash value, a time stamp, and a device fingerprint, multi-hop transmission is realized through a LoRaWAN protocol, and the transmission efficiency is improved by 40 times compared with a traditional method.

[0069] Step S303: A three-level verification system composed of roadside units, regional controllers, and cloud verification nodes is established, and a national encryption SM3 algorithm is used to implement transmission data.

[0070] Among them, the transmission layer verification: each data packet is attached with a device private key signature; Block layer verification: an improved PBFT consensus algorithm is used to verify the block integrity; System layer verification: the consistency of the total data is verified through a Merkle tree.

[0071] Step S304: In the load feature extraction stage, a model watermarking technology is introduced, device registration information and algorithm version number are compiled into implicit watermarks and embedded in the clustering model, and when a k-means++ algorithm generates a three-dimensional feature space, a traceable digital watermark identifier is automatically embedded.

[0072] Step S305: Build a load classification execution framework based on the private chain, compile the A / B / C level load control strategy into a smart contract, and automatically trigger it when a voltage sag occurs.

[0073] Specifically, the core load (Class A) calls the hardware encryption module to perform quantum key distribution. The controllable load (Class C) initiates a flexible control protocol based on zero-knowledge proof.

[0074] Step S306: Deploy the alliance chain monitoring node to execute the full process of control instructions and store evidence.

[0075] The command generation phase records federated learning parameter update logs. The command transmission phase adds multi-level digital signature timestamps. The command execution phase collects the physical layer signatures of device responses. An abnormal event traceability chain is established, supporting tamper-proof verification of operation records within 24 hours.

[0076] It can be seen that this embodiment deeply integrates the blockchain verification mechanism into the power Internet of Things perception layer, the collaborative application mode of model watermarking and federated learning, and constructs a multi-layer cascade audit traceability system. The method can improve the accuracy of abnormal data identification and the control instruction response speed reaches milliseconds, meeting the real-time requirements of highway load management.

[0077] On the basis of the above embodiments, in order to further improve the reliability of the highway load-side dynamic monitoring method provided in the above embodiments, the following is an implementable method. In one embodiment, the highway load-side dynamic monitoring method specifically includes the following steps: Step S401: Collect power supply and distribution system data by deploying intelligent sensor equipment, use dynamic compression coding algorithm to compress the data stream in real time, and add timestamps and data fingerprints.

[0078] In this embodiment, intelligent sensing equipment is deployed in the highway power supply and distribution system to collect data such as power distribution parameters, cable loads, and environmental indicators in real time to form an original data stream. The data stream is compressed in real time through improved adaptive coding: shorter coding symbols are assigned to high-frequency data based on historical data frequency statistics; variable-length coding is used for low-frequency or burst data to improve transmission efficiency; and timestamps and data fingerprints are added to the compressed data to ensure transmission integrity.

[0079] Step S402: Analyze the load characteristics based on the continuity and periodicity indicators, and calculate the adjustment possibility to optimize the encoding parameters.

[0080] This embodiment decompresses and normalizes the compressed data to construct a standardized data set containing features such as power fluctuation rate and harmonic distortion rate. The number of consecutive occurrences and duration of the same load pattern (e.g., tunnel ventilation unit operation) are counted. The mean and fluctuation coefficient of adjacent load pattern intervals are calculated to assess periodic regularity. Combining continuity and periodicity, the adjustment possibility is calculated:

[0081] Among them, L is the normalized continuity index and U is the normalized periodicity index.

[0082] Step S403: Dynamically adjust the coding table according to changes in data characteristics to improve the compression efficiency of high-frequency data.

[0083] This embodiment dynamically adjusts the compression encoding parameters based on the analysis results of step S402. If the adjustment possibility W of a load pattern is greater than 0.2 and the update degree is significant, the update degree calculation formula is:

[0084] Among them, n is the number of times the load pattern occurs in the current cycle, a is the current total load, is the number of historical occurrences, The total amount of historical data. Generate a new coding table and synchronize it to the sensor device to ensure efficient transmission of subsequent data.

[0085] Step S404: Combine the national standard classification criteria and predictive factors to dynamically divide the load levels and generate a multi-objective optimization power supply strategy.

[0086] Based on the load classification (A / B / C), the classification threshold is adjusted in combination with dynamic data characteristics: Class A load: If the continuity index L>0.8 and the periodicity index U>0.7, power supply reliability is mandatory; Class C load: If the adjustment possibility W<0.3, a greater peak shaving and valley filling depth (>40%) is allowed.

[0087] The dynamic power supply strategy is generated by predictive control, and the optimization objective function is:

[0088] in, =(ΔU) / (U) represents the power loss of cables and transformers. λ1 is the voltage deviation weight coefficient, which adjusts the impact of ΔU on the objective function. Adjusting λ2 balances the priorities of voltage stability and other optimization objectives. ΔU is the difference between the actual and rated voltages, i.e., ΔU = Uactual − Urated. ΔU = Uactual − Urated controls voltage fluctuations and ensures power supply quality. λ3 is the frequency deviation weight coefficient, which adjusts the impact of the frequency deviation (|f − f0|) on the objective function. f represents the actual grid frequency, the current operating frequency of the grid; f0 represents the rated grid frequency. λ0 is the adjustment possibility weight coefficient, which adjusts the impact of the load dynamic characteristics W on the objective function.

[0089] Step S405: Verify the validity of the control instructions through the digital twin platform and trigger the adaptive correction mechanism to adjust the reactive compensation device.

[0090] If voltage exceeding the limit or feeder overload is detected, the adaptive correction mechanism is triggered to dynamically adjust the switching combination of reactive compensation devices; the load characteristic knowledge base is updated based on the prediction model: when the tunnel ventilation unit is started, if the lighting system continuity index L>0.6, the lighting power is automatically reduced.

[0091] Step S406: Perform secondary compression storage on the total data sequence based on the update frequency to reduce cloud storage overhead.

[0092] Step S407: Ensure system security through encrypted log recording and parameter self-calibration, and regularly calibrate the coding and classification thresholds.

[0093] Encrypted records are kept for load classification adjustments and equipment start and stop, generating tamper-proof operation logs. Encoded parameters and classification thresholds are regularly calibrated: if the difference between the historical data and real-time data of a load mode exceeds the threshold, the parameter reset process is triggered.

[0094] In an embodiment of the present invention, based on step S106, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0095] Step S801: The protocol data of heterogeneous devices (such as charging piles and lighting systems) in the power supply and distribution system are collected and identified through a multi-protocol parsing engine, stored in a buffer, and subjected to time series preprocessing (denoising, outlier detection, and missing value filling).

[0096] Intelligent sensing equipment is deployed in highway power supply and distribution systems to collect data such as power distribution parameters, cable loads, and environmental indicators in real time. The communication protocols of different devices (such as charging piles and lighting systems) are identified through a multi-protocol parsing engine to extract data types and feature information. The raw data is stored in a data buffer and subjected to time series preprocessing, including denoising, outlier detection, and missing value filling, to improve data quality.

[0097] Step S802: Select a compression algorithm based on the data type and dynamically optimize the compression parameters.

[0098] Specifically, according to the data type, such as continuous time series data or sudden device state data, a compression algorithm is selected. A sliding window compression algorithm combined with an improved Huffman coding is used to reduce redundancy by using data periodicity; an incremental compression algorithm is used to store only the change value to reduce storage overhead.

[0099] Step S803: Deploy the selected compression algorithm to compress the data, and transmit the data with a timestamp and data fingerprint to the cloud after transmission through the edge gateway.

[0100] In this embodiment, the sliding window and Huffman coding combination are configured according to the parameters; the algorithm efficiency is verified through compression testing; the compressed data is attached with a timestamp and data fingerprint, and is transmitted to the cloud through the edge gateway.

[0101] Step S804: According to the national standard grading standard and the compression parameter influence factor, dynamically adjust the compression strategy (such as lossless compression for A level and lossy compression for C level) of the load level (A / B / C level) to generate a multi-objective optimization power supply strategy.

[0102] Step S805: Store the compressed data using the segmented storage and dynamic indexing technology, and decode and splice the incomplete data segments through the preset encoding table (Huffman tree or dictionary mapping).

[0103] In this embodiment, the compressed data is stored in the cloud database, and the segmented storage and dynamic indexing method is used to attach a check code to each data segment to ensure data integrity during decompression.

[0104] Step S806: Deploy the digital twin platform to verify the control instructions, trigger the adaptive mechanism to adjust the reactive power compensation device and the compression parameters, and periodically calibrate the encoding rules to adapt to changes in data patterns.

[0105] If the voltage limit or feeder overload is detected, the adaptive mechanism is triggered to adjust the reactive power compensation device switching strategy. The compression parameters are dynamically modified, such as reducing the compression ratio threshold for C level loads.

[0106] Or periodically calibrate the compression algorithm and grading threshold, which can re-optimize the encoding distribution table according to the differences between historical data and real-time characteristics; update the sliding window size or dictionary mapping rules to adapt to changes in data patterns.

[0107] It can be seen that highway load-side data coexists with continuous time series data (such as changes in cable load over time) and sudden-change device status data (such as the on / off status of lighting systems). Based on the characteristics of different data types, a sliding window compression algorithm combined with improved Huffman coding is selected to process continuous data, leveraging its periodicity to reduce redundancy. An incremental compression algorithm is used to process sudden-change data, storing only the changed values. This targeted algorithm selection improves compression efficiency, reducing network transmission pressure and cloud storage overhead. In terms of load management, this method considers the varying requirements of different load levels for power supply reliability and data integrity. It also dynamically adjusts the compression strategy based on factors influencing compression parameters. This achieves coordinated optimization of data processing and power supply management while ensuring power supply stability.

[0108] Step S805 uses segmented storage and dynamic indexing technology to store compressed data, and decodes and splices incomplete data segments segment by segment through a preset coding table, which is innovative in data storage and restoration. The compressed data is stored in segments and a checksum is attached, and the data is quickly located using a dynamic index to ensure the integrity of the data during storage and transmission. Step S806 verifies the control instructions by deploying a digital twin platform, and triggers an adaptive mechanism to adjust the reactive compensation device and compression parameters. When abnormal conditions such as voltage exceeding the limit or feeder overload are detected, the adaptive mechanism is triggered to adjust the reactive compensation device switching strategy to ensure stable power supply, periodically calibrate the coding rules, and re-optimize the coding allocation table based on the difference between historical data and real-time characteristics, so that the entire monitoring system can continuously adapt to the dynamic changes in the data pattern on the load side of the highway and maintain efficient operation.

[0109] The following is an embodiment of the highway load side dynamic monitoring system provided by the embodiments of the present disclosure. This system and the highway load side dynamic monitoring method of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiments of the highway load side dynamic monitoring system, please refer to the embodiments of the above-mentioned highway load side dynamic monitoring method.

[0110] like Figure 2 As shown, the system includes: The data acquisition module is used to build an IoT sensing network covering a preset section of the highway and collect electrical load indicators in real time; The indicator generation module is used to align electrical load indicators in time and space through the edge computing gateway, and uses a sliding window mechanism to generate a standardized data set containing instantaneous power, load fluctuation rate, and harmonic distortion rate; The analysis and processing module is used to perform cluster analysis on electrical load indicators, construct a three-dimensional feature space based on power factor, active / reactive power ratio, and daily load curve similarity, and set the contour coefficient threshold to achieve pattern recognition of traffic guidance screens, communication base stations, and variable information boards; The load analysis module is used to analyze the temporal correlation between loads, establish a causal chain model for the start-up of tunnel ventilation units and the downshifting of lighting systems, and determine the coupling strength coefficient between the equipment start-up and shutdown thresholds and the surrounding loads; The parameter processing module is used to define and divide the core power load, important guarantee load, and adjustable load using the coupling strength coefficient, and set differentiated QoS parameters; The load analysis module uses core power-maintaining loads, important guarantee loads, and adjustable loads to construct a multi-objective optimization function. This module uses Monte Carlo simulation to predict future load trends for a preset time period and employs model predictive control to optimize the main transformer tap position and reactive compensation device switching combinations. The evaluation and monitoring module is used to use the load trend to obtain the real-time operating parameters of each electrical equipment. Based on the preset evaluation indicators, it calculates the average value and fluctuation range of each indicator in different time periods, compares the calculation results with the preset target values, and evaluates the dynamic monitoring status of the highway load side.

[0111] like Figure 3 As shown, the present application also provides an electronic device, including a display module 103, a memory 102, a processor 101, and a computer program stored in the memory and executable on the processor 101. When the processor 101 executes the program, the steps of the power transmission engineering GIM model parsing and loading method are implemented.

[0112] In the embodiments of the present invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or claimed herein.

[0113] In the embodiment of the present application, the processor 101 can be implemented by using at least one of an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. In some cases, such an embodiment can be implemented in a controller. For software implementation, an embodiment such as a process or function can be implemented with a separate software module that allows the execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a memory and executed by a controller.

[0114] The display module 103 is used to display information input by the user or information provided to the user. The display module 103 may include a display panel, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc.

[0115] The memory 102 can be used to store software programs and various data. The memory 102 can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0116] The present application also provides a storage medium having a computer program stored thereon, which implements the steps of the highway load side dynamic monitoring method when the computer program is executed by a processor.

[0117] The storage medium can be any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0118] In the context of storage media, a readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0119] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for dynamic monitoring of the load side of a highway, characterized in that: Methods include: S101: Build an IoT sensing network to collect electrical load indicators in real time; S102: Use the edge computing gateway to perform spatiotemporal alignment of electrical load indicators and generate a standardized data set using a sliding window mechanism; S103: Perform cluster analysis on electrical load indicators, construct a three-dimensional feature space, and set a silhouette coefficient threshold to achieve pattern recognition of traffic guidance screens, communication base stations, and variable information boards; S104: Analyze the temporal correlation between loads, establish a causal chain model for the start-up of tunnel ventilation units and the downshifting of lighting systems, and determine the coupling strength coefficient between the equipment start-up and shutdown thresholds and the surrounding loads; S105: Define and classify core power loads, important power loads, and adjustable loads based on the coupling strength coefficient, and set differentiated QoS parameters; S106: Construct a multi-objective optimization function, combine it with Monte Carlo simulation to predict the load trend for a preset time in the future, and use model predictive control to optimize the main transformer tap position and the switching combination of reactive power compensation devices in a rolling manner; S107: Based on the load trend, obtain the real-time operating parameters of each electrical device, calculate the average value and fluctuation range of each indicator in different time periods based on the preset evaluation indicators, compare the calculation results with the preset target values, and evaluate the dynamic monitoring status of the highway load side.

2. The method for dynamic monitoring of the highway load side according to claim 1, characterized in that: Step S103 specifically includes: Preprocessing electrical load index data; Construct a three-dimensional feature space based on power factor, active / reactive ratio, and daily load curve similarity; The DTW algorithm is used to calculate the similarity of daily load curves, and the relevant data of each electrical device is mapped into the three-dimensional feature space to form corresponding feature points; Select a clustering algorithm to perform cluster analysis on feature points in the three-dimensional feature space; The optimal K value is determined by combining the elbow rule, and K cluster centers are randomly initialized. Each feature point is assigned to the closest cluster according to the distance between the feature point and the cluster center. The center of each cluster is recalculated, and the distribution of cluster centers and feature points is continuously updated iteratively until the clustering results converge and the silhouette coefficient threshold is obtained.

3. The method for dynamic monitoring of the highway load side according to claim 1, characterized in that: Step S105 specifically includes: evaluating the impact intensity between devices by the power change correlation when the devices are started and stopped; Among them, a dynamic correlation matrix is ​​established to record the power fluctuation impact of the start-stop operation load of different equipment, and the time series correlation of power changes is analyzed using the cross-correlation function. Combined with the physical connection relationship between the equipment, the correlation weight of the core equipment and auxiliary equipment is determined; Divide load levels based on the dual standards of coupling strength coefficient and equipment importance; Set differentiated power supply guarantee strategies for different levels of loads; Establish an adaptive adjustment system based on real-time monitoring data, triggering the recalculation of grading standards when equipment aging or operating condition changes are detected; combine Monte Carlo simulation to predict future load trends and dynamically optimize QoS parameter thresholds; When voltage exceeds the limit or feeder is overloaded, the hierarchical strategy upgrade is automatically triggered.

4. The method for dynamic monitoring of the highway load side according to claim 1, characterized in that: Step S101 also includes: deploying intelligent sensor devices with blockchain node functions in the highway power supply and distribution system, synchronously generating digital certificates with timestamps when collecting electrical load indicators, and building a decentralized sensing network through a star topology structure; The original electrical data is dynamically compressed and encoded using a preset algorithm, and data blocks are generated according to a preset time period. Each block contains a triple check code of the preceding hash value, timestamp, and device fingerprint; Establish a three-level verification system consisting of roadside units, regional controllers, and cloud verification nodes, and use the national secret SM3 algorithm to implement transmission data; Model watermarking technology is introduced during the load feature extraction phase. Device registration information and algorithm version numbers are compiled into implicit watermarks and embedded into the clustering model. When the k-means++ algorithm generates a three-dimensional feature space, a traceable digital watermark is automatically embedded. A load-grading execution framework is built based on a private chain, and the load control strategy is compiled into a smart contract, which is automatically triggered when a voltage sag occurs.

5. The method for dynamic monitoring of the highway load side according to claim 1, characterized in that: Step S107 also includes: using a dynamic compression coding algorithm to compress the real-time operating parameters of each electrical device in real time, and adding a timestamp and data fingerprint; Analyze load characteristics based on continuity and periodicity indicators and calculate adjustments to optimize encoding parameters; Dynamically adjust the coding table according to changes in data characteristics; Combining national standard classification criteria with predictive factors, dynamically divide load levels and generate multi-objective optimization power supply strategies; Verify the effectiveness of control instructions through the digital twin platform, triggering the adaptive correction mechanism to adjust the reactive power compensation device; Perform secondary compression storage on the total data sequence based on the update frequency to reduce cloud storage overhead; System security is ensured through encrypted logging and parameter self-calibration, and coding and classification thresholds are calibrated regularly.

6. The method for dynamic monitoring of the highway load side according to claim 5, characterized in that: The steps of dynamically adjusting the coding table according to changes in data characteristics specifically include: If the adjustment possibility W of a load pattern is greater than 0.2 and the updating degree is significant, the updating degree calculation formula is: Among them, n is the number of times the load pattern occurs in the current cycle, a is the current total load, is the number of historical occurrences, is the total amount of historical data; The load levels are divided into: A, B, and C, and the classification thresholds are adjusted based on dynamic data characteristics; The dynamic power supply strategy is generated by predictive control, and the optimization objective function is: in, is the power loss of cables and transformers, λ1 is the voltage deviation weight coefficient, ΔU is the difference between the actual voltage and the rated voltage, λ2 is the frequency deviation weight coefficient, which is used to adjust the weight coefficient of the frequency deviation (|f − f0|) on the objective function; f is the actual grid frequency, f0 is the rated grid frequency; λ3 is the adjustment possibility weight coefficient.

7. The method for dynamic monitoring of the highway load side according to claim 5, characterized in that: Step S106 further includes: The multi-protocol parsing engine collects and identifies protocol data from heterogeneous devices in the power supply and distribution system, stores it in a buffer, and performs timing preprocessing. Select compression algorithm based on data type and dynamically optimize compression parameters; Deploy the selected compression algorithm to compress the data, attach a timestamp and data fingerprint, and then transmit it to the cloud; Dynamically adjust the compression strategy of load levels and generate multi-objective optimization power supply strategies; Use segmented storage and dynamic indexing technology to store compressed data, decode segment by segment through preset coding tables and splice incomplete data segments; Configure the digital twin platform to verify control instructions, trigger the adaptive mechanism to adjust the reactive compensation device and compression parameters, and periodically calibrate the encoding rules to adapt to data pattern changes.

8. A dynamic monitoring system for the load side of a highway, characterized in that: The system is used to implement the highway load side dynamic monitoring method according to any one of claims 1 to 7; The system includes: The data acquisition module is used to build an IoT sensing network covering a preset section of the highway and collect electrical load indicators in real time; The indicator generation module is used to align electrical load indicators in time and space through the edge computing gateway, and uses a sliding window mechanism to generate a standardized data set containing instantaneous power, load fluctuation rate, and harmonic distortion rate; The analysis and processing module is used to perform cluster analysis on electrical load indicators, construct a three-dimensional feature space based on power factor, active / reactive power ratio, and daily load curve similarity, and set the contour coefficient threshold to achieve pattern recognition of traffic guidance screens, communication base stations, and variable information boards; The load analysis module is used to analyze the temporal correlation between loads, establish a causal chain model for the start-up of tunnel ventilation units and the downshifting of lighting systems, and determine the coupling strength coefficient between the equipment start-up and shutdown thresholds and the surrounding loads; The parameter processing module is used to define and divide the core power load, important guarantee load, and adjustable load using the coupling strength coefficient, and set differentiated QoS parameters; The load analysis module uses core power-maintaining loads, important guarantee loads, and adjustable loads to construct a multi-objective optimization function. This module uses Monte Carlo simulation to predict future load trends for a preset time period and employs model predictive control to optimize the main transformer tap position and reactive compensation device switching combinations. The evaluation and monitoring module is used to use the load trend to obtain the real-time operating parameters of each electrical equipment. Based on the preset evaluation indicators, it calculates the average value and fluctuation range of each indicator in different time periods, compares the calculation results with the preset target values, and evaluates the dynamic monitoring status of the highway load side.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the highway load side dynamic monitoring method as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the highway load side dynamic monitoring method as claimed in any one of claims 1 to 7 are implemented.

Images