Distributed multi-device cooperation method and system based on event-triggered communication

Abstract

The invention provides a distributed multi-device cooperation method and system based on event-triggered communication, and the method comprises the steps: obtaining a real-time state sensing data set of a distributed device cluster in a power system, carrying out the analysis of the device association characteristics of the real-time state sensing data set, obtaining the operation synchronization characteristics and environment interference coupling characteristics between devices, and carrying out the analysis of the operation association characteristics between the devices; and calling a pre-trained collaborative decision model to carry out collaborative degree evaluation processing on the inter-device operation synchronization characteristics and the environment interference coupling characteristics, generating a device collaborative priority sequence, determining a communication resource allocation scheme according to the device collaborative priority sequence, and executing distributed device communication control operation based on the communication resource allocation scheme. And generating a cooperative communication instruction, and issuing the instruction to the corresponding equipment to realize multi-equipment cooperative operation. According to the invention, communication conflicts or delays caused by improper resource allocation can be reduced, so that the distributed devices can operate cooperatively and efficiently under the double constraints of operation synchronism and environmental adaptability, and the overall stability of multi-device cooperation is improved.

Description

Technical Field

[0001] This invention relates to the field of equipment collaborative control technology, and in particular to a distributed multi-device collaborative method and system based on event-triggered communication. Background Technology

[0002] With the increasing intelligence of power systems, the collaborative operation of distributed devices has become a crucial element in ensuring stable and efficient system operation. Distributed device collaboration refers to the technology of coordinating the communication and operation of multiple devices to jointly complete specific tasks in complex environments. Currently, common methods for distributed device collaboration typically involve acquiring device operation command data, analyzing the time synchronization or type matching of operation commands between devices, and formulating communication resource allocation schemes based on these single-dimensional operational characteristics, such as fixed allocation of communication links or setting a unified interaction frequency. However, this collaboration method, which relies solely on operational synchronization, fails to consider the mutual influence of interference factors in the device's environment. For example, although two devices may have highly synchronized operation commands, their communication quality may degrade due to sharing the same interference source. Conversely, devices with average operational synchronization may be more suitable for priority communication due to lower environmental interference coupling. This leads to a discrepancy between resource allocation and actual collaboration needs, easily causing communication conflicts or delays and affecting the stability of multi-device collaborative operation. Summary of the Invention

[0003] In view of this, the present invention provides a distributed multi-device collaboration method and system based on event-triggered communication. The technical solution of the embodiments of the present invention is implemented as follows: On one hand, embodiments of the present invention provide a distributed multi-device collaboration method based on event-triggered communication, the method comprising: Acquire a real-time status perception data set of a distributed device cluster in a power system. The real-time status perception data set includes operation instruction records, operating mode identifiers, and environmental interference detection information of each device. The real-time status perception data group is subjected to device association feature parsing processing to obtain inter-device operation synchronization features and environmental interference coupling features; The pre-trained collaborative decision-making model is invoked to evaluate the degree of collaboration between the inter-device operation synchronization features and the environmental interference coupling features, and a device collaboration priority sequence is generated. A communication resource allocation scheme is determined based on the device collaboration priority sequence, and the communication resource allocation scheme includes the selection rules for inter-device communication links and the information interaction frequency adjustment rules. Based on the communication resource allocation scheme, a distributed device communication control operation is performed to generate a collaborative communication instruction containing a communication link identifier and interaction frequency parameters, and the collaborative communication instruction is sent to the corresponding device to achieve multi-device collaborative operation.

[0004] On the other hand, embodiments of the present invention provide a computer system including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the program to implement the steps in the above-described method.

[0005] The distributed multi-device collaboration method based on event-triggered communication provided by this invention can comprehensively capture the operating status of distributed devices and external environmental influencing factors by acquiring a real-time status perception data set containing operation command records, operating mode identifiers, and environmental interference detection information. This data set is then processed through device association feature analysis to obtain inter-device operation synchronization features and environmental interference coupling features. This ensures that collaborative decision-making not only relies on the synchronization of device operations but also considers the mutual influence of environmental interference between devices, providing a more realistic two-dimensional basis for collaborative evaluation. A pre-trained collaborative decision-making model is invoked to evaluate the collaboration degree of the two-dimensional features and generate a device collaboration priority sequence, avoiding the limitations of traditional methods that rely solely on a single feature or fixed rules. This makes the priority sequence more reflective of the actual collaborative needs between devices. A communication resource allocation scheme, including link selection rules and interaction frequency adjustment rules, is determined based on the priority sequence, achieving dynamic matching between resource allocation and device collaboration needs. Finally, communication control is executed and collaborative communication commands are issued based on this scheme, effectively reducing communication conflicts or delays caused by improper resource allocation. This allows distributed devices to operate more efficiently under the dual constraints of operational synchronization and environmental adaptability, thereby improving the overall stability and reliability of multi-device collaboration. Attached Figure Description

[0006] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present invention and, together with the specification, serve to explain the technical solutions of the present invention.

[0007] Figure 1 This is a schematic diagram illustrating the implementation process of a distributed multi-device collaboration method based on event-triggered communication, provided in an embodiment of the present invention.

[0008] Figure 2 This is a schematic diagram of the hardware entity of a computer system provided in an embodiment of the present invention. Detailed Implementation

[0009] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on 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.

[0010] This invention provides a distributed multi-device collaboration method based on event-triggered communication, which can be executed by a processor of a computer system. The computer system can refer to a backend server of a power system.

[0011] Figure 1 This is a schematic diagram illustrating the implementation process of a distributed multi-device collaboration method based on event-triggered communication provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes: Step S100: Obtain the real-time status perception data group of the distributed equipment cluster in the power system. The real-time status perception data group includes the operation instruction records, operation mode identifiers and environmental interference detection information of each device.

[0012] Real-time status awareness data sets refer to the data collection obtained by real-time monitoring of the current status of distributed equipment clusters during the operation of a power system. Operation instruction records are records of various operation instructions received by the equipment and their execution status, such as equipment start-up, stop, and adjustment instructions, along with their corresponding execution time and results, reflecting the equipment's operational history and instruction execution trajectory over a period of time. Operating mode identifiers are used to clearly identify the current operating mode of the equipment. Different operating modes represent different ways the equipment operates, such as normal operation mode, energy-saving operation mode, and emergency operation mode. These modes affect the equipment's operating parameters and performance. Environmental interference detection information is data obtained by detecting potential interference factors in the equipment's environment, including but not limited to electromagnetic interference, temperature changes, humidity changes, and vibration. These interference factors may affect the normal operation of the equipment.

[0013] Acquiring real-time status awareness data sets can be achieved by deploying various sensors and monitoring devices within the power system. For example, for operation command recordings, command execution log files can be extracted from the device's control system; these log files record detailed information about each operation command. Operating mode identifiers can be obtained by reading the device's status registers or configuration files. For environmental interference detection information, electromagnetic sensors can be used to detect electromagnetic interference intensity, temperature and humidity sensors can be used to monitor ambient temperature and humidity respectively, and vibration sensors can be used to detect device vibration. Integrating these data acquired through different methods yields the real-time status awareness data sets for the distributed device clusters within the power system.

[0014] Step S200: Perform device association feature parsing on the real-time status perception data group to obtain the inter-device operation synchronization features and environmental interference coupling features.

[0015] Device association feature parsing and processing refers to in-depth analysis and mining of real-time status perception data sets to identify feature information reflecting the relationships between devices. Device operation synchronization features describe the degree of synchronization in the execution of operation commands by different devices, i.e., whether the operation commands of different devices are consistent in time, whether the command types match, and whether the execution goals are consistent. Environmental interference coupling features reflect the degree of mutual influence between interference factors in the environment in which different devices are located, such as the spatial overlap of environmental interference sources affecting different devices and the correlation of changes in interference intensity.

[0016] Various data analysis and mining techniques can be employed to perform device association feature parsing on real-time status awareness data sets. For example, time series analysis methods can be used to process operation command records to identify the time synchronization relationship between device operations; spatial analysis methods can be used to process environmental interference detection information to determine the distribution range of environmental interference sources and the coupling relationship of interference between devices.

[0017] As one implementation method, step S200 can be specifically implemented as the following steps S210~S250: Step S210: Perform time-series alignment processing on the operation instruction records in the real-time status awareness data group to generate a timestamp sequence of operation instructions for each device.

[0018] Timing alignment refers to adjusting and arranging the operation command records of different devices according to a unified time standard to eliminate the deviation between the device's local clock and the global clock, thereby making the operation commands of each device comparable in time. A timestamp sequence is a sequence obtained by converting the trigger time of the operation command into discrete data points containing timestamps, and then classifying and organizing them according to device identifiers. This sequence clearly shows the time order of the operation commands of each device.

[0019] Timing alignment of operation command records can be achieved through the following specific steps. First, the time standard of the global clock needs to be defined. This global clock can be a unified clock source for the power system, such as the standard time provided by a Network Time Protocol (NTP) server. Then, each operation command record is processed to extract the command trigger time and command completion time, constructing a command time interval including start and end times. Next, using the global clock as a reference, time offset correction is performed on the command time intervals of each device. By calculating the time difference between the device's local clock and the global clock, the command time intervals are adjusted accordingly to eliminate time deviations. Afterward, the corrected command time intervals are arranged chronologically to generate an independent operation command timeline for each device. Then, time point sampling processing is performed on the operation command timelines of each device, extracting command trigger event points on the timelines at preset time intervals. Finally, these command trigger event points are converted into discrete data points containing timestamps and categorized by device identifier, thereby generating a timestamp sequence of operation commands for each device.

[0020] As one implementation method, step S210 can be specifically implemented as the following steps S211~S215: Step S211: Extract the instruction trigger time and instruction completion time from each operation instruction record, and construct an instruction time interval that includes the start time and end time.

[0021] The instruction trigger time point refers to the moment when the operation instruction begins execution, while the instruction completion time point is the moment when the operation instruction is completed. The instruction time interval is a period of time determined by the instruction trigger time point and the instruction completion time point, which can clearly represent the execution duration of the operation instruction.

[0022] The trigger and completion times of instructions can be extracted by searching and parsing the log files containing the operation instructions. These log files record instruction-related information in a defined format, such as timestamps indicating the trigger and completion times. Text parsing techniques can be used to extract the trigger and completion times from each operation instruction record according to the log file's format rules. Then, these two timestamps can be used as the start and end times, respectively, to construct an instruction time interval that includes both the start and end times.

[0023] Step S212: Using the system global clock as a reference, perform time offset correction processing on the instruction time interval of each device to eliminate the deviation between the device's local clock and the global clock.

[0024] The system global clock is the unified time standard in the power system, providing a precise time reference for the entire system. Device local clocks, on the other hand, are the clocks used by each individual device. Due to various factors, device local clocks may deviate from the global clock. Time offset correction processing calculates the time difference between the device's local clock and the global clock, and adjusts the device's command time interval accordingly to eliminate this deviation, ensuring that the command time intervals of each device are comparable under the global time standard.

[0025] There are several methods to determine the discrepancy between a device's local clock and the global clock. One method is to use the Network Time Protocol (NTP) for clock synchronization and discrepancy measurement. The device can periodically communicate with an NTP server to obtain the accurate time of the global clock and calculate the time difference between the local clock and the global clock. Another method is to use a high-precision time synchronization device, such as a Global Positioning System (GPS) clock, which obtains the precise time by receiving GPS signals and compares it with the device's local clock to determine the time discrepancy.

[0026] After obtaining the deviation between the device's local clock and the global clock, time offset correction processing can be performed on the instruction time intervals of each device. If the device's local clock is faster than the global clock, the corresponding time offset value is subtracted from all instruction time intervals of that device; if the device's local clock is slower than the global clock, the corresponding time offset value is added to all instruction time intervals of that device.

[0027] Step S213: Arrange the corrected instruction time intervals in chronological order to generate an independent operation instruction time axis for each device.

[0028] An operation command timeline is a time sequence formed by arranging device operation commands in chronological order. It visually displays the execution order and time intervals of device operation commands. Sorting the corrected command time intervals can be done using sorting algorithms, such as quicksort or mergesort. These algorithms can sort the command time intervals based on their start or end time, ensuring that the command time intervals are arranged in chronological order. After sorting, these ordered command time intervals are connected sequentially to generate an independent operation command timeline for each device.

[0029] Step S214: Perform time point sampling processing on the operation command timeline of each device, and extract the command trigger event points on the timeline in units of preset time intervals.

[0030] Time-point sampling refers to traversing the timeline of operation commands at preset time intervals to extract command triggering event points. The preset time interval is a fixed length pre-set based on specific analysis needs and data characteristics. Command triggering event points are the points in time when the operation command begins execution. By extracting these event points, the discrete distribution of the operation commands on the timeline can be obtained, facilitating subsequent analysis and processing.

[0031] When performing time-point sampling, starting from the start time of the operation command timeline, the process moves forward sequentially according to preset time intervals, checking for the existence of a command trigger event at the end of each time interval. If a trigger event exists, it is extracted. This process can be implemented using a loop. For example, assuming the preset time interval is 5 seconds and the start time of the operation command timeline is "2024-01-01 13:00:00", then starting from this time point, a check is performed every 5 seconds to see if a command trigger event exists. If there is a command trigger event at "2024-01-01 13:02:00" and another at "2024-01-01 13:07:00", then both event points are extracted.

[0032] Step S215: Convert the instruction trigger event point into discrete data points containing timestamps, and then classify and organize them according to the device identifier to generate a timestamp sequence of each device operation instruction.

[0033] A command trigger event point is the specific time point at which an operation command begins execution. Converting it into discrete data points containing timestamps facilitates data storage and analysis. A timestamp is a number or string representing a specific point in time, typically containing information such as year, month, day, hour, minute, and second. Discrete data points represent command trigger event points as independent data, with each data point containing a timestamp. Categorizing by device identifier involves grouping command trigger event points from different devices separately to distinguish the time sequences of operation commands from different devices.

[0034] Converting instruction trigger event points into discrete data points containing timestamps can be achieved by encoding the time information of the instruction trigger event points according to a set format. For example, the time information can be converted to Unix timestamp format, that is, the number of seconds elapsed from January 1, 1970, 00:00:00 UTC (Coordinated Universal Time) to the instruction trigger event point. Then, each discrete data point containing a timestamp is associated with a corresponding device identifier, and these data points are categorized and organized according to the device identifier.

[0035] For example, consider devices E and F. The instruction triggering event points extracted from the operation instruction timeline of device E are "2024-01-01 14:00:00" and "2024-01-01 14:05:00", while those from device F are "2024-01-01 14:02:00" and "2024-01-01 14:06:00". Converting these event points to Unix timestamp format yields discrete data points for device E (1704002400, 1704002700) and device F (1704002520, 1704002760). These are then categorized and organized according to device identifiers to obtain the respective operation instruction timestamp sequences for devices E and F.

[0036] Step S220: Analyze the time overlap region of operation instructions from different devices in the timestamp sequence, and extract the type matching degree and execution target consistency parameters of the operation instructions in the overlap region as operation synchronization features between devices.

[0037] The time overlap region refers to the portion of the timestamp sequence of operation instructions from different devices that overlaps in time. Type matching degree refers to the proportion of operation instructions of the same type from different devices within the time overlap region, reflecting the consistency of operation instruction types across devices. The execution target consistency parameter determines the degree of consistency in the execution targets of operation instructions across different devices by analyzing the description information of the execution targets. Inter-device operation synchronization characteristics describe the degree of synchronization in the execution of operation instructions across different devices. By analyzing the time overlap region, type matching degree, and execution target consistency parameter, the inter-device operation synchronization can be comprehensively evaluated.

[0038] Time series analysis methods can be used to analyze overlapping regions in operation instructions from different devices within a timestamp sequence. First, the timestamp sequences from different devices are aligned. Then, these sequences are traversed to identify overlapping portions in time. This process can be implemented using interval overlap detection algorithms. After identifying the overlapping regions, the number of instructions of the same type within these regions is counted, and their proportion to the total number of instructions is calculated to obtain the type matching degree. The consistency parameter of the execution target can be determined by calculating the semantic similarity of the execution target description information of the operation instructions. Natural language processing techniques, such as word vector models (e.g., Word2Vec) and cosine similarity calculation methods, can be used to convert the execution target description information into a vector representation and calculate the cosine similarity between vectors to measure the consistency of the execution target.

[0039] As one implementation method, step S220 can be specifically implemented as the following steps S221~S225: Step S221: Select any two timestamp sequences from two devices for time overlap detection processing, and calculate the ratio of the number of event points in the same time interval between the two timestamp sequences as the time overlap rate.

[0040] Time overlap detection processing refers to comparing and analyzing the timestamp sequences of two devices to identify intervals where they overlap in time. The event point ratio refers to the proportion of event points in the timestamp sequences of the two devices within the same time interval to their respective total event points. The time overlap rate measures the degree of temporal overlap between the operational instructions of two devices and is an important indicator for assessing the operational synchronization between devices.

[0041] Time overlap detection can be performed using an interval comparison algorithm. First, the timestamp sequences of the two devices are sorted chronologically. Then, each time interval is compared sequentially to find their overlapping portion. After determining the overlapping interval, the number of event points for both devices within that interval is counted. Assuming device I has n1 event points in its timestamp sequence and device J has n2 event points, and within the overlapping interval, device I has m1 event points and device J has m2 event points, then the time overlap rate can be calculated using the following formula: Time overlap rate = (m1 + m2) / (n1 + n2).

[0042] Step S222: For device pairs whose time overlap rate reaches a preset threshold, extract the operation instruction types within their overlapping time intervals, and count the proportion of the same type of instruction as the type matching degree.

[0043] The preset threshold is a critical value for time overlap rate pre-set based on actual needs and experience, used to filter out device pairs whose operation instructions have a high degree of temporal overlap. The overlapping time interval refers to the portion of the timestamp sequences of two devices that overlaps in time. Operation instruction type is a classification of operation instructions, such as start, stop, and adjustment instructions. Type matching degree refers to the proportion of the same type of instruction to the total number of instructions within the overlapping time interval, reflecting the consistency of the device pair in terms of operation instruction type.

[0044] For device pairs with a time overlap rate reaching a preset threshold, further analysis of their operation command types within the overlapping time interval is needed. Command information within the overlapping time interval can be extracted from the device's operation command records, and the command types can be categorized and statistically analyzed. Assuming the total number of commands for the device pair within the overlapping time interval is N, and the number of commands of the same type is M, then the type matching degree = M / N.

[0045] Step S223: Analyze the execution target description information of each operation instruction within the overlapping time interval, and determine the consistency parameter of the instruction execution target through semantic similarity calculation.

[0046] The execution target description information is a textual description of the goal to be achieved by the operation instruction, including the specific intent and expected effect of the instruction. Semantic similarity calculation refers to the process and analysis of text information to calculate the degree of semantic similarity between different texts. The consistency parameter of the instruction execution target is used to measure the degree of consistency of operation instructions on different devices in terms of execution targets. Through semantic similarity calculation, the execution target description information can be quantified to obtain a parameter that reflects the degree of consistency.

[0047] Semantic similarity calculations can be performed using various natural language processing techniques. One approach is to convert the target description information into a vector representation and then calculate the similarity between the vectors. For example, a word vector model (such as Word2Vec) can be used to convert each word in the target description information into a vector, and then operations such as averaging or summing the vectors of the entire description information are performed to obtain a unified vector representation. Next, the cosine similarity calculation method is used to calculate the cosine value of the angle between the two vectors, and this cosine value can be used as a measure of semantic similarity.

[0048] For example, the execution goal of an operation instruction from device M is described as "improving device operating efficiency by 10%", and the execution goal of an operation instruction from device N is described as "increasing device operating efficiency by 10%". These two descriptions are converted into vectors using a word vector model, and their cosine similarity is calculated to obtain a similarity value. This similarity value can then be used as a parameter to determine the degree of consistency between the execution goals of these two instructions.

[0049] Step S224: Perform a weighted summation of the time overlap rate, type matching degree, and execution target consistency parameters to generate a comprehensive synchronization index that reflects the degree of synchronization between devices.

[0050] Weighted summation involves assigning different weights to the parameters of time overlap rate, type matching degree, and execution target consistency, and then summing these parameters after multiplying them by their respective weights. The comprehensive synchronization index is an indicator that comprehensively considers time overlap rate, type matching degree, and execution target consistency, used to fully reflect the degree of operational synchronization between devices.

[0051] The weights can be adjusted based on actual circumstances and needs. For example, if time overlap rate is considered more important in evaluating the synchronization between devices, it can be assigned a larger weight; if type matching and execution target consistency are also considered crucial, they can be assigned appropriate weights. Assuming the weight of time overlap rate is w1, type matching is w2, and execution target consistency parameter is w3, and w1 + w2 + w3 = 1, then the comprehensive synchronization index = time overlap rate × w1 + type matching × w2 + execution target consistency parameter × w3.

[0052] Step S225: Associate and store the comprehensive synchronization index with the device identifier to form a set of inter-device operation synchronization features containing the device pair identifier and the corresponding comprehensive synchronization index.

[0053] Device identifiers are information used to uniquely identify each device, such as the device number and name. Device pair identifiers, on the other hand, are information used to uniquely identify a pair of devices. Associating and storing the comprehensive synchronization index with the device identifiers means binding the comprehensive synchronization index of each device pair to its corresponding device pair identifier, and storing this information in a data structure to form a set of inter-device operation synchronization characteristics.

[0054] A database or data file can be used to store the set of operational synchronization characteristics between devices. In a database, a table can be created with fields including device pair identifiers and a comprehensive synchronization metric. The calculated comprehensive synchronization metric for each device pair and its corresponding device pair identifier are then inserted into the table. In a data file, a CSV (comma-separated values) file format can be used, with each row containing the device pair identifier and comprehensive synchronization metric, separated by commas.

[0055] Step S230: Perform spatial correlation analysis on the environmental interference detection information in the real-time status perception data group to identify the distribution range of interference sources and the trend of interference intensity changes in the environment where each device is located.

[0056] Spatial correlation analysis refers to analyzing environmental interference detection information to identify spatial relationships. The distribution range of interference sources refers to the spatial area covered by interference sources in the environment, which can be determined by analyzing and clustering the location information of the interference sources. The interference intensity variation trend refers to the change in the interference intensity of the interference sources over time, including trends such as increase, decrease, and fluctuation. Identifying the distribution range of interference sources and the interference intensity variation trend in the environment of each device helps to understand the interference situation in the environment where the equipment is located, providing a reference for subsequent collaborative operation of the equipment.

[0057] Spatial correlation analysis of environmental interference detection information can be performed using Geographic Information System (GIS) technology and data analysis methods. First, the location coordinates and intensity values ​​of interference sources are extracted from the environmental interference detection information, constructing feature points containing these coordinates and intensity values. Then, spatial clustering analysis algorithms are used to cluster these feature points, identifying clusters of interference sources with the same interference type. The boundary coordinate range of each cluster is determined as the distribution range of the interference sources. For the trend of interference intensity variation, the interference intensity values ​​within the same cluster of interference sources can be arranged chronologically to generate a time-varying sequence of interference intensity. This sequence is then subjected to trend fitting processing to calculate the temporal slope and periodic fluctuation amplitude parameters of the interference intensity, thereby obtaining the long-term direction of change and short-term fluctuation characteristics of the interference intensity.

[0058] As one implementation method, step S230 can be specifically implemented as the following steps S231~S235: Step S231: Extract the location coordinates and intensity values ​​of the interference source from each piece of environmental interference detection information, and construct interference source feature points containing location coordinates and intensity values.

[0059] Interference source location coordinates refer to the specific spatial location information of the interference source, which can be represented by latitude and longitude coordinates or Cartesian coordinates. Interference intensity value is a numerical value that quantifies the degree of interference generated by the interference source; for example, electromagnetic interference intensity can be represented by electromagnetic field strength, and temperature interference can be represented by the temperature change amplitude. Interference source feature points are data points formed by combining the interference source's location coordinates and interference intensity values, and can serve as the basis for subsequent spatial correlation analysis.

[0060] Extracting the location coordinates and intensity values ​​of interference sources from environmental interference detection information can be done by processing the data according to the specific detection equipment and data format. If a sensor with positioning capabilities is used, it will directly record the location coordinates and intensity values ​​of the interference source, and this information can be extracted from the sensor's data records. If multiple sensors are used in combination for detection, it may be necessary to fuse and process the data from different sensors to determine the location coordinates and intensity values ​​of the interference source.

[0061] Step S232: Perform spatial clustering analysis on the feature points of the interference sources to identify the clustered regions of interference sources with the same interference type, and determine the boundary coordinate range of each clustered region as the distribution range of the interference sources.

[0062] Spatial clustering analysis involves grouping spatially located interference source feature points with the same interference type together to form different clusters. The same interference type means that the interference sources produce interference with similar properties, such as both being electromagnetic interference or both being temperature interference. An interference source clustering region is a spatial area composed of interference source feature points with the same interference type. The boundary coordinate range refers to the spatial boundary location information of each clustering region, which can be represented by coordinate values. By determining the boundary coordinate range, the distribution range of the interference sources can be clearly defined.

[0063] Spatial clustering analysis can be performed using various clustering algorithms, such as K-Means and DBSCAN. Taking DBSCAN as an example, this algorithm clusters data points based on their density, automatically identifying densely populated regions as clusters. First, two parameters need to be set: the neighborhood radius ε and the minimum number of points MinPts. For each interference source feature point, the number of points within its neighborhood radius ε is calculated. If the number of points is greater than or equal to the minimum number of points MinPts, then that point is a core point. Starting from the core point, other points within its neighborhood are added to the same cluster, and this process continues until no more points can be added. This process is repeated until all interference source feature points have been processed.

[0064] After obtaining the clusters, it is necessary to determine the boundary coordinate range of each cluster region. This boundary coordinate range can be determined by calculating the maximum and minimum values ​​of the position coordinates of all interference source feature points within the cluster. For example, for an electromagnetic interference source cluster region, its boundary coordinate range can be represented as [x...]. min ,x max ;y min ,y max ], where x min and x max These are the minimum and maximum x-coordinates of all interference source feature points in the cluster, respectively, and y-coordinates. min and y max These are the minimum and maximum values ​​of the y-coordinate, respectively.

[0065] Step S233: Arrange the interference intensity values ​​within the same interference source cluster area in chronological order to generate sequence data of interference intensity changing over time.

[0066] A cluster of interference sources refers to a region composed of interference sources of the same type, obtained through spatial clustering analysis. Arranging interference intensity values ​​in chronological order means sorting the interference intensity values ​​detected at different time points within the same interference source cluster according to their chronological sequence. The time-series data of interference intensity variation is a time series composed of interference intensity values, reflecting the changes in the interference intensity of the interference source over a period of time.

[0067] Interference intensity values ​​at different time points within the same interference source cluster area can be extracted from environmental interference detection information, and these values ​​can be sorted according to time information. For example, within an electromagnetic interference source cluster area, the electromagnetic interference intensity values ​​detected at different time points are "Time 1: 30dB; Time 2: 35dB; Time 3: 32dB". Arranging these values ​​in chronological order yields the sequence data of interference intensity changing over time as [30, 35, 32].

[0068] To ensure the accuracy of the time sequence, accurate timestamps need to be recorded when collecting environmental interference detection information. A high-precision clock device can be used to provide a time reference for the detection equipment, or the time of the detection equipment can be synchronized via Network Time Protocol (NTP).

[0069] Step S234: Perform trend fitting processing on the sequence data, calculate the time change slope of the interference intensity and the periodic fluctuation amplitude parameters, and generate the interference intensity change trend that reflects the long-term change direction and short-term fluctuation characteristics of the interference intensity.

[0070] Trend fitting refers to fitting a mathematical model to the time-series data of interference intensity to identify the trend of change. The time-varying slope refers to the rate at which the interference intensity changes over time, reflecting the long-term direction of change. The periodic fluctuation amplitude parameter refers to the range of fluctuation of the interference intensity within a certain period, reflecting the short-term fluctuation characteristics of the interference intensity. The interference intensity change trend is a comprehensive description of the long-term direction of change and short-term fluctuation characteristics of the interference intensity over a period of time.

[0071] Various methods can be used for trend fitting, such as linear regression, multinomial regression, and moving average. Taking linear regression as an example, suppose the sequence data of disturbance intensity changing over time is y=[y1,y2,...,yn], and the corresponding time points are x=[x1,x2,...,xn]. The least squares method can be used to fit a straight line y=ax+b, where a is the slope over time and b is the intercept. The calculated slope a can determine the long-term direction of the disturbance intensity. If a>0, the disturbance intensity shows an upward trend; if a<0, the disturbance intensity shows a downward trend.

[0072] For periodic fluctuation amplitude parameters, methods such as Fourier transform or wavelet transform can be used to analyze the sequence data, identify the periodic components, and calculate their fluctuation amplitudes. For example, Fourier transform can be used to convert the sequence data to the frequency domain to identify the main frequency components and their corresponding amplitudes, which can be used as periodic fluctuation amplitude parameters.

[0073] Step S235: Associate and store the distribution range of interference sources and the trend of interference intensity changes with the device identifier to form an environmental interference characteristic description for each device.

[0074] The device identifier is used to uniquely identify each device, while the distribution range of interference sources and the trend of interference intensity variation are descriptive information about the interference factors in the environment in which the device is located. Associating the distribution range of interference sources and the trend of interference intensity variation with the device identifier means binding the distribution range of interference sources and the trend of interference intensity variation corresponding to each device, and storing this information in a data structure to form a description of the environmental interference characteristics corresponding to each device.

[0075] A database or data file can be used to store descriptions of environmental interference characteristics. In a database, a table can be created with fields including device identifier, interference source distribution range, and interference intensity variation trend. The interference source distribution range and interference intensity variation trend for each device can then be inserted into the table. In a data file, JSON (JavaScript Object Notation) format can be used, with each object containing information such as device identifier, interference source distribution range, and interference intensity variation trend.

[0076] For example, the interference source distribution range corresponding to device S is "[(x1,y1),(x2,y2),(x3,y3)]", and the interference intensity variation trend is "time variation slope: 0.3dB / hour; periodic fluctuation amplitude: 3dB". This information is associated with the device identifier "device S" and stored in the database. A record is inserted into the data table, where the device identifier is "device S", the interference source distribution range is "[(x1,y1),(x2,y2),(x3,y3)]", and the interference intensity variation trend is "time variation slope: 0.3dB / hour; periodic fluctuation amplitude: 3dB". Summarizing these records forms the environmental interference characteristic description for each device.

[0077] Step S240: Calculate the spatial overlap area and intensity change correlation parameters of environmental interference detection information of different devices, and generate environmental interference coupling characteristics that reflect the degree of mutual influence between environmental interference between devices.

[0078] Spatial overlap region refers to the portion of the environment in which the distribution ranges of interference sources in different devices overlap spatially. Intensity change correlation parameter refers to the degree of correlation between the trends of interference intensity changes in different devices, which can be determined by performing correlation analysis on the time-series data of interference intensity changes. Environmental interference coupling characteristics are used to describe the degree of mutual influence of environmental interference between different devices. By calculating the spatial overlap region and intensity change correlation parameter, the coupling of environmental interference between devices can be comprehensively assessed.

[0079] Spatial overlap regions can be calculated using Geographic Information System (GIS) technology or spatial geometric calculation methods. For example, if the distribution range of interference sources is represented by polygons, the spatial overlap region can be determined by calculating the intersection area between the polygons. For correlation parameters related to intensity changes, correlation coefficients, such as the Pearson correlation coefficient, can be used for measurement. First, extract time-series data on the interference intensity changes of different devices, and then calculate the Pearson correlation coefficient between these data sequences. This coefficient ranges from -1 to 1; the closer the absolute value is to 1, the stronger the correlation; the closer the absolute value is to 0, the weaker the correlation.

[0080] As one implementation method, step S240 can be specifically implemented as the following steps S241~S245: Step S241: Select any two devices to describe the environmental interference characteristics and extract the boundary coordinates of their interference source distribution range.

[0081] Environmental interference feature description is a detailed description of interference factors in the environment in which the device is located, including information such as the distribution range of interference sources and the trend of interference intensity changes. The boundary coordinates of the interference source distribution range refer to the spatial boundary position information of the interference source distribution area, which can be represented by coordinate values. Extracting the boundary coordinates of the interference source distribution range is to prepare for subsequent calculation of the spatial overlapping area. The extraction of the boundary coordinates of the interference source distribution range from the environmental interference feature description can be processed according to the specific data format. If the environmental interference feature description is stored in text form, the text needs to be parsed to extract the boundary coordinate information. If it is stored in the form of a data structure, such as a JSON object or database record, the boundary coordinate information can be obtained directly from the data structure. For example, if the environmental interference feature description of device V is "interference source distribution range: [(x1,y1),(x2,y2),(x3,y3)]", by parsing this description, the boundary coordinates of the interference source distribution range can be extracted as [(x1,y1),(x2,y2),(x3,y3)].

[0082] Step S242: Calculate the ratio of the area of ​​the spatial intersection region of the distribution ranges of the two interference sources to the area of ​​their respective distribution ranges, and generate an overlap area ratio parameter that reflects the degree of spatial overlap of the interference sources.

[0083] The spatial intersection area refers to the area of ​​the overlapping region between the distribution ranges of two interference sources. The area of ​​each distribution range refers to the total area of ​​the distribution range of each interference source. The overlap area ratio parameter is the ratio of the spatial intersection area to the area of ​​each distribution range, which can intuitively reflect the degree of spatial overlap between the distribution ranges of the two interference sources.

[0084] The area of ​​the spatial intersection region and the area of ​​each individual distribution range can be calculated using Geographic Information System (GIS) software or spatial geometric calculation methods. If the distribution ranges of the interference sources are represented by polygons, the area of ​​the spatial intersection region can be calculated using a polygon intersection algorithm, and the area of ​​each individual distribution range can be calculated using a polygon area calculation algorithm. Assuming the area of ​​the spatial intersection region of the distribution ranges of two interference sources is S1, and the areas of their respective distribution ranges are S2 and S3, the overlap area ratio parameter can be calculated using the following formula: Overlap area ratio parameter = S1 / (S2+S3-S1).

[0085] Step S243: Extract time series data of the interference intensity change trend of the two devices, and calculate the correlation parameter of the two time series as the intensity change correlation parameter.

[0086] Time series data on interference intensity trends refers to the sequence of interference intensity changes over time, reflecting the variation of interference intensity from the interference source over a period of time. The correlation parameter is an indicator used to measure the degree of association between two time series; by calculating this parameter, the correlation between the interference intensity trends of different devices can be determined.

[0087] The time-series data on the variation trend of interference intensity between two devices can be obtained from the environmental interference feature description. The previous steps have already generated the time-series data on the variation of interference intensity for each device; these data can be extracted directly.

[0088] There are several methods for calculating the correlation parameters between two time series, such as the Pearson correlation coefficient and the Spearman correlation coefficient.

[0089] Step S244: Analyze the correlation between the overlapping area ratio parameter and the intensity change correlation parameter, and construct an environmental interference coupling degree evaluation function.

[0090] The correlation refers to the inherent relationship between the overlap area ratio parameter and the intensity change correlation parameter. This relationship may manifest as a positive correlation, a negative correlation, or a non-linear relationship. The environmental interference coupling degree assessment function is a mathematical function used to comprehensively evaluate the degree of environmental interference coupling between devices. It takes the overlap area ratio parameter and the intensity change correlation parameter as inputs and outputs a numerical value reflecting the degree of environmental interference coupling between devices.

[0091] The correlation between the overlapping area percentage parameter and the intensity change correlation parameter can be analyzed using data visualization and statistical analysis methods. For example, a scatter plot can be drawn, with the overlapping area percentage parameter as the x-axis and the intensity change correlation parameter as the y-axis, to observe the distribution of data points and determine the correlation between the two. If a linear relationship is found, a linear regression model can be used to construct an environmental interference coupling degree assessment function. Assuming the overlapping area percentage parameter is x and the intensity change correlation parameter is y, the environmental interference coupling degree assessment function can be expressed as: f(x,y)=ax+by+c, where a, b, and c are coefficients determined through regression analysis.

[0092] Step S245: Calculate the environmental interference coupling degree value between devices through the environmental interference coupling degree evaluation function, associate the coupling degree value with the device pair identifier and store it to form an environmental interference coupling feature set containing the device pair identifier and the corresponding coupling degree value.

[0093] The environmental interference coupling degree value is calculated by substituting the overlap area ratio parameter and intensity change correlation parameter of the device pair into the environmental interference coupling degree evaluation function. This value is used to measure the degree of mutual influence of environmental interference between devices. Linking the coupling degree value with the device pair identifier allows for a clear record of the environmental interference coupling status of each device pair, facilitating subsequent querying and analysis of the environmental interference relationships between devices.

[0094] When calculating the environmental interference coupling degree, the overlapping area ratio parameter and intensity change correlation parameter of the device pair are first obtained from the previously calculated data. Then, these parameters are substituted into the environmental interference coupling degree evaluation function for calculation.

[0095] To store this information, a database or file storage method can be used. In a database, a dedicated table can be created to store the set of environmental interference coupling characteristics. The table fields can include device pair identifiers and environmental interference coupling values. The calculated environmental interference coupling value for each device pair and its corresponding device pair identifier are then inserted into the table. If file storage is used, a CSV file can be employed, with each row containing the device pair identifier and environmental interference coupling value, separated by commas.

[0096] Step S250: Input the inter-device operation synchronization features and environmental interference coupling features into the feature association module for cross-validation processing, and filter out the effective set of association features that simultaneously satisfy operation synchronization and environmental interference coupling.

[0097] The feature association module is a functional module used to comprehensively analyze and process the operational synchronization features and environmental interference coupling features between devices. It can determine the correlation and effectiveness between these features through preset rules and algorithms. Cross-validation processing refers to the mutual verification of operational synchronization features and environmental interference coupling features within this module, identifying feature combinations that perform well in both aspects. The effective association feature set is obtained after screening and contains a set of feature combinations that simultaneously meet the requirements of operational synchronization and environmental interference coupling. These feature combinations can more accurately reflect the collaborative relationship between devices.

[0098] After the inter-device operation synchronization characteristics and environmental interference coupling characteristics are input into the feature association module, the module analyzes and compares these characteristics according to preset rules and algorithms. For example, for each pair of devices, the module checks whether their operation synchronization characteristics and environmental interference coupling characteristics meet certain preset conditions, such as whether the operation synchronization index reaches a certain threshold and whether the environmental interference coupling value is within a reasonable range. If both the operation synchronization characteristics and environmental interference coupling characteristics of a pair of devices meet these conditions, the relevant feature combinations of that pair are filtered out and included in the set of valid association features.

[0099] As one implementation method, step S250 can be specifically implemented as the following steps S251-S255: Step S251: Obtain the conflict patterns of device operation synchronization characteristics and environmental interference coupling characteristics recorded in the historical collaborative failure case library. The conflict patterns include feature combinations with high operation synchronization but low environmental interference coupling and feature combinations with low operation synchronization but high environmental interference coupling.

[0100] The historical collaborative failure case database is a database storing information on failed cases during past device collaborative operations. It records the operational synchronization characteristics and environmental interference coupling characteristics of each failed case. Conflict modes refer to inconsistencies or mismatches between operational synchronization characteristics and environmental interference coupling characteristics in these failed cases. A combination of high operational synchronization but low environmental interference coupling indicates that the devices have high synchronization in executing operational commands, but little mutual influence in terms of environmental interference. This situation may lead to problems due to environmental differences during collaborative operation. Conversely, a combination of low operational synchronization but high environmental interference coupling indicates poor synchronization in executing operational commands, but significant mutual influence in terms of environmental interference, which may also affect the collaborative effect of the devices.

[0101] Retrieving conflict patterns from a historical database of collaborative failure cases can be achieved through database queries. Tables can be created in the database to store information about failed cases. Table fields can include device pair identifiers, operational synchronization characteristics, and environmental interference coupling characteristics. By writing SQL queries, records matching the characteristics of high operational synchronization but low environmental interference coupling, or low operational synchronization but high environmental interference coupling, can be filtered out. Organizing these records yields the conflict patterns. For example, the database can be queried for records where the operational synchronization index is greater than a certain threshold, while the environmental interference coupling value is less than another threshold, and records where the operational synchronization index is less than a certain threshold, while the environmental interference coupling value is greater than another threshold.

[0102] Step S252: Input the inter-device operation synchronization features and environmental interference coupling features into the conflict detection submodule of the feature association module, perform matching analysis with the conflict pattern, and identify device pairs with feature conflicts.

[0103] The conflict detection submodule is a sub-functional module within the feature association module, specifically designed to detect conflicts between device operation synchronization features and environmental interference coupling features. Matching analysis involves comparing and analyzing the input device pair features with conflict patterns in the historical collaboration failure case library to determine if the device pair's features match the conflict pattern. If a match is found, it indicates that the device pair has feature conflicts, which may cause problems during collaborative operation.

[0104] After inputting the inter-device operation synchronization features and environmental interference coupling features into the conflict detection submodule, the submodule iterates through each conflict mode in the historical collaboration failure case library and compares the features of the current device pair with these modes. Similarity calculation methods can be used to determine feature matching. For example, for operation synchronization features and environmental interference coupling features, their similarity to the corresponding features in the conflict modes can be calculated separately. If the similarity exceeds a certain threshold, the features of the device pair are considered to match the conflict mode. For instance, Euclidean distance can be used to calculate the similarity between feature vectors; when the distance is less than a certain preset value, a match is determined.

[0105] Step S253: For device pairs that have not been identified as having conflicting features, extract the comprehensive synchronization index from the inter-device operation synchronization features and the coupling degree value from the environmental interference coupling features, and calculate the synchronization coupling correlation parameter between the two. The synchronization coupling correlation parameter is characterized by the product relationship between the comprehensive synchronization index and the coupling degree value.

[0106] For device pairs without identified characteristic conflicts, it indicates that they do not exhibit significant incoordination in terms of operational synchronization and environmental interference coupling. The comprehensive synchronization index, calculated in the previous steps, measures the degree of operational synchronization between devices; the coupling degree value, calculated using the environmental interference coupling degree evaluation function, measures the degree of mutual influence of environmental interference between devices. The synchronization coupling correlation parameter is an index that comprehensively considers both operational synchronization and environmental interference coupling. It is obtained by multiplying the comprehensive synchronization index by the coupling degree value, and can more comprehensively reflect the cooperative relationship between device pairs in terms of operation and environmental interference.

[0107] After extracting the comprehensive synchronization index and coupling degree value of the device pairs with unidentified feature conflicts, the synchronization coupling correlation degree parameter can be obtained by directly multiplying the two values.

[0108] Step S254: Set the minimum threshold for the synchronization coupling correlation parameter, and filter out feature combinations of devices whose synchronization coupling correlation parameter is higher than the threshold.

[0109] The minimum threshold is a pre-set value used to filter out device pairs with high synchronization coupling characteristics. By setting the minimum threshold, device pairs that perform well in both operational synchronization and environmental interference coupling can be further filtered out, and these device pairs are more likely to achieve good results in cooperative operation.

[0110] The minimum threshold can be adjusted based on actual needs and experience. For example, if you want to filter out device pairs with very good synergy, you can set the minimum threshold higher; if you want to cover more device pairs, you can set the minimum threshold lower. After determining the minimum threshold, compare the synchronization coupling correlation parameters of all device pairs that have not been identified as having feature conflicts, and filter out device pair feature combinations that are higher than the threshold.

[0111] Step S255: Associate the selected feature combinations with the device pair identifier and store them to generate an effective set of associated features that simultaneously satisfies operational synchronization and environmental interference coupling.

[0112] The purpose of associating the selected feature combinations with device pair identifiers is to bind the feature combination of each device pair that meets the requirements of operational synchronization and environmental interference coupling to the corresponding device pair identifier, facilitating subsequent management and use. The effective associated feature set, obtained after filtering and organization, contains a set of device pair feature combinations that simultaneously meet the requirements of operational synchronization and environmental interference coupling, providing more accurate and useful information for subsequent device collaborative decision-making.

[0113] A database or data file can be used to store the effective set of associated features. In the database, a table can be created with fields including device pair identifier, comprehensive synchronization index, coupling degree value, and synchronization coupling correlation parameter. The relevant information for the selected device pairs is then inserted into the table. In the data file, a CSV file format can be used, with each row containing the device pair identifier and corresponding feature parameters, separated by commas.

[0114] Step S300: Call the pre-trained collaborative decision-making model to evaluate the degree of collaboration between devices based on the operational synchronization characteristics and environmental interference coupling characteristics, and generate a sequence of device collaboration priorities.

[0115] The pre-trained collaborative decision-making model is an artificial intelligence model trained on a large amount of data. It can evaluate the degree of collaboration between devices based on the input characteristics of inter-device operation synchronization and environmental interference coupling. The collaboration evaluation process involves inputting these characteristics into the collaborative decision-making model, which then analyzes and calculates them according to pre-defined algorithms and rules, outputting an evaluation value reflecting the degree of collaboration between devices. The device collaboration priority sequence is a sequence obtained by ranking the device pairs based on the collaboration evaluation results. This helps determine which device pairs have higher priority in collaborative operation, thereby rationally allocating communication resources and arranging collaborative tasks.

[0116] When invoking the pre-trained collaborative decision-making model, the inter-device operation synchronization features and environmental interference coupling features are first organized and input according to the model's required format. For example, if the model requires the input to be in vector form, features such as the comprehensive synchronization index and coupling degree value are converted into vectors. After receiving the input, the model performs calculations and inferences through its internal neural network structure, ultimately outputting a collaboration degree evaluation value for each device pair. Based on these evaluation values, the device pairs are sorted in descending order to generate a device collaboration priority sequence.

[0117] As one implementation method, step S300 can be specifically implemented as the following steps S310-S350: Step S310: Input the comprehensive synchronization index in the inter-device operation synchronization feature and the coupling degree value in the environmental interference coupling feature into the feature fusion layer of the collaborative decision-making model, and perform normalization processing to eliminate the difference in dimensions.

[0118] The feature fusion layer is a crucial layer in collaborative decision-making models. Its main function is to fuse and process different types of features for subsequent analysis and computation. Normalization involves converting the comprehensive synchronization index and coupling degree values ​​to a unified numerical range, typically [0,1]. This eliminates dimensional differences between different features, making the model more fair and accurate in processing them. Dimensional differences refer to the fact that the comprehensive synchronization index and coupling degree values ​​may have different value ranges and units. Without normalization, the model might assign higher weights to features with larger value ranges, thus affecting the accuracy of the evaluation results.

[0119] After the comprehensive synchronization index and coupling degree value are input into the feature fusion layer of the collaborative decision-making model, a normalization algorithm is used within the layer to process these values. Normalization algorithms include, for example, Min-Max normalization or Z-Score normalization. In this way, both the comprehensive synchronization index and coupling degree value are transformed to the [0,1] interval, eliminating dimensional differences.

[0120] Step S320: The normalized comprehensive synchronization index and coupling degree value are cross-correlationally analyzed through the correlation analysis layer of the collaborative decision-making model to generate a joint feature vector that reflects the synergistic effect of operation and environmental interference between equipment.

[0121] The correlation analysis layer is a crucial layer in the collaborative decision-making model used for in-depth analysis and mining of the normalized comprehensive synchronization index and coupling degree values. It identifies the correlations and synergistic effects among these features. Cross-correlation analysis involves comparing and analyzing the comprehensive synchronization index and coupling degree values ​​at this layer. Through a series of calculations and transformations, a joint feature vector is generated that reflects the synergistic effects of operational and environmental interference between devices. This joint feature vector is a multi-dimensional vector that integrates the characteristics of operational synchronization and environmental interference coupling, providing a more comprehensive description of the collaborative relationships between devices.

[0122] In the correlation analysis layer, various algorithms and methods are employed to process the normalized comprehensive synchronization index and coupling degree values. For example, these values ​​are subjected to differencing and covariance calculations to extract differences and correlation information. Then, this information is integrated and its dimensions are expanded to generate a joint feature vector.

[0123] As one implementation method, step S320 can be specifically implemented as the following steps S321-S325: Step S321: Perform differential processing on the normalized comprehensive synchronization index and coupling degree value, and calculate the absolute value of the difference between the two as the synergistic effect difference parameter.

[0124] Differential processing is a mathematical operation used to calculate the difference between two values. In this step, the normalized integrated synchronization index and coupling value are differentially processed. By calculating the absolute value of their difference, a value reflecting the degree of difference between operational synchronization and environmental interference coupling can be obtained, namely the synergistic effect difference parameter. This parameter helps to understand the degree of imbalance between operational synchronization and environmental interference in the equipment.

[0125] Assume the normalized overall synchronization index is x norm The coupling degree value is y norm Then the synergistic effect difference parameter d=|x norm -y norm |

[0126] Step S322: Extract the time series data of the comprehensive synchronization index and coupling degree value, and calculate the covariance value of the two time series as the correlation parameter of synergy.

[0127] Time series data refers to numerical sequences of composite synchronization indicators and coupling values ​​changing over a period of time. These sequences can reflect the changes in operational synchronization between equipment and environmental interference coupling over time. Covariance is a statistic used to measure the linear relationship between two random variables. In this step, the covariance value of the time series data of composite synchronization indicators and coupling values ​​is calculated. The result can be used as a correlation parameter of synergy, describing the degree of association between operational synchronization between equipment and environmental interference coupling. After extracting the time series data of composite synchronization indicators and coupling values, the covariance is calculated according to the formula.

[0128] Step S323: Perform dimensional expansion processing on the synergistic effect difference parameter and the synergistic effect correlation parameter to generate a two-dimensional feature vector containing the difference dimension and the correlation dimension.

[0129] Dimensional expansion processing refers to expanding the synergistic effect difference parameter and synergistic effect correlation parameter from one-dimensional numerical values ​​to two-dimensional vectors. This more clearly represents the information contained in these two parameters and facilitates subsequent analysis and processing. A two-dimensional feature vector is a vector containing information in two dimensions: one dimension represents the synergistic effect difference parameter, and the other dimension represents the synergistic effect correlation parameter. It can more comprehensively describe the relationship between the operational synchronicity between devices and the coupling of environmental interference. The synergistic effect difference parameter and the synergistic effect correlation parameter are combined into a two-dimensional vector.

[0130] Step S324: Perform principal component analysis on the two-dimensional feature vector to extract the principal components that can explain most of the data variance as core collaborative features.

[0131] Principal Component Analysis (PCA) is a data dimensionality reduction and feature extraction method that can transform high-dimensional data into low-dimensional data while retaining the main information in the data. In this step, PCA is performed on the two-dimensional eigenvectors. By calculating the eigenvalues ​​and eigenvectors of the covariance matrix of the eigenvectors, the principal components that can explain most of the data variance are identified. The core collaborative features, extracted after PCA, represent the main relationships between operational synchronicity and environmental interference coupling between devices, reducing the dimensionality of the data and improving the computational efficiency and accuracy of the model.

[0132] When performing principal component analysis on two-dimensional eigenvectors, the covariance matrix S of the two-dimensional eigenvectors is first calculated. Assume the two-dimensional eigenvectors are... If the sample size is n, then the covariance matrix is... ,in It is the average value of the two-dimensional eigenvectors. Then, solve for the eigenvalues ​​of the covariance matrix S. and and the corresponding feature vectors and Typically, eigenvectors with larger eigenvalues ​​are selected as principal components. The two-dimensional eigenvectors are then projected onto these principal components to obtain the core collaborative features. For example, if... > Then the two-dimensional feature vector is projected onto The projection value obtained is the core collaborative feature.

[0133] Step S325: Concatenate the core collaborative features with the original comprehensive synchronization index and coupling degree value to generate a joint feature vector containing multi-dimensional information.

[0134] The splicing process refers to combining the core collaborative features with the original comprehensive synchronization indicators and coupling degree values ​​to form a vector containing more dimensions of information. The resulting joint feature vector integrates the original information of core collaborative features, operational synchronization, and environmental interference coupling, which can more comprehensively describe the collaborative relationship between devices and provide richer evidence for subsequent collaborative degree evaluation.

[0135] Step S330: The joint feature vector is weighted and summed using the evaluation calculation layer of the collaborative decision-making model. The weights of the operation synchronization index and the environmental interference coupling degree are dynamically adjusted based on historical collaborative effect data.

[0136] The evaluation and calculation layer is the layer in the collaborative decision-making model used for the final evaluation and calculation of the joint feature vector. It can perform weighted summation of each dimension of the joint feature vector according to preset weights to obtain the collaboration score between devices. The weights of the operation synchronization index and the environmental interference coupling degree are parameters used to adjust the importance of the operation synchronization and environmental interference coupling features in the joint feature vector. They are not fixed, but dynamically adjusted according to historical collaboration effect data to adapt to different collaboration scenarios and needs.

[0137] In the evaluation computation layer, the weights w1 for the operation synchronization index, w2 for the environmental interference coupling degree, and w3 for the core collaborative features need to be determined first, with w1 + w2 + w3 = 1. Then, the joint feature vector V = (c, x norm ,y norm The weighted summation is performed, and the synergy score is calculated as: score = w3c + w1x norm +w2y norm .

[0138] As one implementation method, step S330 can be specifically implemented as the following steps S331-S336: Step S331: Construct a historical collaboration effect database, which includes the collaboration score of historical device pairs, the stability index of actual collaborative operation, and the communication resource utilization index.

[0139] The historical collaboration effect database is a database used to store relevant effect data during past device collaboration operations, providing data support for subsequent weight adjustments. The collaboration score, obtained during previous collaboration assessments, measures the degree of collaboration between devices. The actual collaborative operation stability index is a quantitative description of the stability of devices during collaborative operation, such as device failure rate and fluctuations in operating parameters. The communication resource utilization index refers to the efficiency of communication resource usage during device collaborative communication, such as bandwidth utilization and communication latency.

[0140] A historical collaboration performance database can be built using a relational database management system, such as MySQL or Oracle. Create corresponding tables in the database to store the collaboration scores, actual collaborative operation stability indicators, and communication resource utilization indicators for historical device pairs. Table fields can include device pair identifiers, collaboration scores, actual collaborative operation stability indicators, and communication resource utilization indicators. Organize and store the relevant data on past device collaboration operations according to the table structure for subsequent querying and analysis.

[0141] Step S332: Perform correlation analysis on the historical collaborative effect database, calculate the first correlation coefficient between the operation synchronization index and the collaborative operation stability, and the second correlation coefficient between the environmental interference coupling degree and the communication resource utilization rate.

[0142] Correlation analysis involves statistically analyzing data from a historical collaborative performance database to identify the relationships between different variables. The first correlation coefficient is a statistic used to measure the linear relationship between operational synchronization indicators and collaborative operational stability, helping to understand the impact of inter-device operational synchronization on collaborative operational stability. The second correlation coefficient is a statistic used to measure the linear relationship between environmental interference coupling and communication resource utilization, helping to understand the impact of inter-device environmental interference coupling on communication resource utilization.

[0143] When performing correlation analysis on a historical database of collaborative performance, the Pearson correlation coefficient can be used to calculate the first and second correlation coefficients. Assuming the operational synchronization index is X1, the collaborative operation stability index is Y1, the environmental interference coupling degree is X2, the communication resource utilization index is Y2, and the sample size is n, then the first correlation coefficient... Second correlation coefficient ,in These are the average values ​​of the corresponding variables.

[0144] Step S333: Determine the initial allocation ratio of the operation synchronization index weight and the environmental interference coupling degree weight based on the ratio of the first correlation coefficient and the second correlation coefficient.

[0145] The ratio of the first correlation coefficient to the second correlation coefficient reflects the relative importance of operational synchronization indicators and environmental interference coupling to the stability of collaborative operation and the utilization rate of communication resources. This ratio allows for the determination of the initial allocation ratio of the weights for operational synchronization indicators and environmental interference coupling, enabling a more reasonable consideration of the impact of operational synchronization and environmental interference coupling on the degree of coordination during the weighted summation process.

[0146] Assuming the first correlation coefficient is r1, the second correlation coefficient is r2, the operational synchronization index weight is w1, and the environmental interference coupling degree weight is w2, and w1 + w2 = 1, the initial allocation ratio of w1 and w2 can be determined based on the ratio of r1 / r2. For example, if r1 / r2 > 1, it indicates that the operational synchronization index has a greater impact on the stability of coordinated operation, so the proportion of w1 can be appropriately increased; if r1 / r2 < 1, it indicates that the environmental interference coupling degree has a greater impact on the utilization rate of communication resources, so the proportion of w2 can be appropriately increased. One allocation method is... .

[0147] Step S334: During the real-time coordination evaluation process, extract the current equipment pair's coordination operation stability monitoring value and communication resource utilization monitoring value, and calculate the deviation between them and the historical best coordination effect.

[0148] The real-time coordination evaluation process refers to the evaluation of the coordination degree between devices during current collaborative operation. Cooperative operation stability monitoring values ​​refer to the actual numerical values ​​of device collaborative operation stability obtained during real-time monitoring, such as the real-time failure rate of devices and real-time fluctuations in operating parameters. Communication resource utilization monitoring values ​​refer to the actual utilization efficiency of communication resources obtained during real-time monitoring, such as real-time bandwidth utilization and real-time communication latency. Historical best coordination effect refers to the relevant indicator values ​​of the device pair with the best collaborative operation stability and communication resource utilization performance in the historical coordination effect database. Deviation refers to the difference between the current device pair's cooperative operation stability monitoring values ​​and communication resource utilization monitoring values ​​and the historical best coordination effect, reflecting the gap between the current device pair's coordination effect and the historical best situation.

[0149] During real-time coordination evaluation, corresponding monitoring sensors and systems are deployed on the devices to acquire real-time monitoring values ​​for the coordinated operational stability and communication resource utilization of the current device pair. Then, relevant index values ​​for historical best coordination performance are retrieved from the historical coordination performance database, and the deviation between the current monitoring value and the historical best value is calculated. For example, if the current device pair's coordinated operational stability monitoring value is S... current The historical best collaborative operation stability index is S. optimal Then the stability deviation of coordinated operation DS=|S current -S optimal |;The current device's communication resource utilization monitoring value is U current The historical best communication resource utilization rate index is U optimal Then the deviation in communication resource utilization DU = |U current -U optimal |

[0150] Step S335: Dynamically adjust the weights of the operation synchronization index and the environmental interference coupling degree based on the deviation amount. If the deviation amount of the collaborative operation stability is greater than the deviation amount of the communication resource utilization rate, then increase the weight of the operation synchronization index; otherwise, increase the weight of the environmental interference coupling degree.

[0151] Dynamically adjusting the weights of the operation synchronization index and the environmental interference coupling degree according to the deviation amount is to make the synergy degree evaluation more adaptable to the real-time device collaboration situation. If the deviation amount of the collaborative operation stability is greater than the deviation amount of the communication resource utilization rate, it indicates that the collaborative operation stability problem of the current device pair is more prominent, and the operation synchronization has a greater impact on the collaborative operation stability. Therefore, it is necessary to increase the weight of the operation synchronization index to enhance the importance of operation synchronization in the synergy degree evaluation. On the contrary, if the deviation amount of the communication resource utilization rate is greater than the deviation amount of the collaborative operation stability, it indicates that the current communication resource utilization rate problem is more prominent, and the environmental interference coupling has a greater impact on the communication resource utilization rate. Therefore, it is necessary to increase the weight of the environmental interference coupling degree to enhance the importance of environmental interference coupling in the synergy degree evaluation.

[0152] During the real-time synergy degree evaluation process, compare the magnitudes of the deviation amount of the collaborative operation stability DS and the deviation amount of the communication resource utilization rate DU. If DS > DU, then on the basis of the current weights, appropriately increase the weight w1 of the operation synchronization index, and at the same time correspondingly decrease the weight w2 of the environmental interference coupling degree. For example, w1' = w1 + α, w2' = w2 - α, where α is an adjustment step size set according to the actual situation. If DS < DU, then appropriately increase the weight w2 of the environmental interference coupling degree, and at the same time correspondingly decrease the weight w1 of the operation synchronization index. For example, w1' = w1 - α, w2' = w2 + α.

[0153] Step S336: Perform a weighted summation process on the joint feature vector based on the adjusted weights to generate a dynamically optimized synergy degree score value.

[0154] After dynamically adjusting the weights of the operation synchronization index and the environmental interference coupling degree according to the deviation amount, perform a weighted summation process on the joint feature vector using the adjusted weights. The joint feature vector is a multi-dimensional vector generated in the previous steps, containing core collaborative features, original comprehensive synchronization indexes, and coupling degree values. Through weighted summation, the feature information of each dimension can be integrated to obtain a value reflecting the collaboration degree between devices, that is, a dynamically optimized synergy degree score value. This score value takes into account the real-time device collaboration situation and the correlation of historical data, and can more accurately evaluate the collaboration degree between devices.

[0155] Step S340: Take the weighted summation result as the synergy degree score value between devices, and sort the device pairs in descending order according to the synergy degree score value.

[0156] After obtaining the dynamically optimized collaboration score, this score is used as the final collaboration score between devices. The collaboration scores of all device pairs are collected and organized, and then the device pairs are sorted in descending order of score. The purpose of this sorting is to determine the priority of device pairs in collaborative operation; device pairs with higher collaboration scores have higher priority in collaborative operation and are able to obtain communication resources and collaborative task allocations more quickly.

[0157] Sorting algorithms, such as quicksort or mergesort, can be used to sort the synergy scores of the device pairs. During the sorting process, the identifier and corresponding synergy score of each device pair are recorded simultaneously.

[0158] Step S350: Generate a device collaboration priority sequence containing device pair identifiers and corresponding collaboration score values ​​based on the sorting results.

[0159] The device collaboration priority sequence is a list containing device pair identifiers and their corresponding collaboration scores, arranged from highest to lowest according to collaboration score. This sequence visually demonstrates the priority order of each device pair during collaborative operation, providing a basis for subsequent communication resource allocation and collaborative task scheduling.

[0160] Based on the sorting results, the identifiers and corresponding collaboration scores of each device pair are compiled into a list, with the elements in the list arranged in descending order of collaboration scores. For example, if the sorted device pairs and their collaboration scores are: device pair C (score 0.9), device pair A (score 0.7), and device pair B (score 0.5), then the generated device collaboration priority sequence is: [(device pair C, 0.9), (device pair A, 0.7), (device pair B, 0.5)].

[0161] Step S400: Determine the communication resource allocation scheme based on the device collaboration priority sequence. The communication resource allocation scheme includes the selection rules for communication links between devices and the adjustment rules for information exchange frequency.

[0162] Communication resource allocation schemes aim to rationally allocate communication resources during collaborative operation, ensuring efficient and stable communication between devices. Device collaboration priority sequences reflect the priority of each device pair in collaborative operation, allowing for the development of more rational communication resource allocation strategies. Communication link selection rules refer to how to choose the appropriate communication link from among many available links based on the device pair's priority and communication needs. Information exchange frequency adjustment rules refer to adjusting the frequency of information exchange between devices based on their priority and collaboration status to improve communication efficiency and collaboration effectiveness.

[0163] When determining a communication resource allocation scheme, the first step is to analyze the device collaboration priority sequence. For device pairs with higher priority, their communication resource needs are guaranteed first. For communication link selection, the most suitable link can be chosen from available links based on factors such as the physical location of the device pair, communication bandwidth requirements, and communication latency requirements. For example, for device pairs that are close together, a wired communication link can be selected to improve communication stability and bandwidth; for device pairs that are far apart, a wireless communication link can be selected to increase communication flexibility. The rules for adjusting the information exchange frequency can be adjusted based on the collaboration score and real-time collaboration status of the device pairs. For device pairs with higher collaboration scores, the information exchange frequency can be appropriately increased to better achieve collaboration; for device pairs with lower collaboration scores, the information exchange frequency can be appropriately decreased to reduce the waste of communication resources.

[0164] As one implementation method, step S400 can be specifically implemented as the following steps S410-S450: Step S410: Extract the device pairs in the device collaboration priority sequence whose collaboration score reaches the preset threshold as priority collaboration device pairs.

[0165] The preset threshold is a critical value for the collaboration score set in advance based on actual needs and experience. It is used to filter out device pairs with high collaboration scores. Priority collaboration device pairs refer to device pairs whose collaboration scores reach or exceed the preset threshold. These device pairs have higher priority in collaborative operation, and their communication resources and collaborative tasks need to be guaranteed first.

[0166] When extracting priority collaborative device pairs from the device collaboration priority sequence, each device pair in the sequence and its collaboration score are traversed, and device pairs with collaboration scores greater than or equal to a preset threshold are selected. For example, if the preset threshold is 0.7 and the device collaboration priority sequence is [(device pair C, 0.9), (device pair A, 0.7), (device pair B, 0.5)], then the priority collaborative device pairs are device pair C and device pair A.

[0167] Step S420: Allocate a dedicated communication link for the priority cooperating device pair, where the bandwidth resources of the dedicated communication link are prioritized over the shared communication link of other device pairs.

[0168] A dedicated communication link is a communication link specifically allocated to priority collaborative devices. It can provide more stable and higher bandwidth communication services to meet the communication needs of priority collaborative devices. Bandwidth resource priority means that during the communication resource allocation process, dedicated communication links can use bandwidth resources first. When bandwidth resources are scarce, the bandwidth of shared communication links for other devices may be limited, while the bandwidth of dedicated communication links can be guaranteed.

[0169] When allocating a dedicated communication link to a pair of priority coordinating devices, it is first necessary to understand the available communication link resources, including the link type (e.g., wired link, wireless link), bandwidth capacity, and current load. Then, based on factors such as the physical location and communication needs of the priority coordinating device pair, a suitable link is selected from the available links as the dedicated communication link. For example, for two priority coordinating device pairs that are close to each other and have high communication bandwidth requirements, a high-speed wired fiber optic link can be selected as the dedicated communication link.

[0170] As one implementation method, step S420 can be specifically implemented as the following steps S421-S426: Step S421: Obtain a list of available link resources in the power system communication network. The list of available link resources includes link identifier, maximum bandwidth capacity, and current load rate.

[0171] The available link resource list is a summary of information on all available communication links in the power system communication network. It includes basic information for each link, such as link identifier, maximum bandwidth capacity, and current load rate. The link identifier is used to uniquely identify each communication link, such as the link number and name. Maximum bandwidth capacity refers to the maximum data transmission rate that each communication link can provide, such as 100Mbps or 1Gbps. The current load rate refers to the proportion of bandwidth currently being used by each communication link relative to its maximum bandwidth capacity, reflecting the link's activity level.

[0172] Obtaining a list of available link resources in a power system communication network can be achieved by interacting with the network's management system. The management system typically records and manages information about all communication links in the network. By sending a query request to the management system, the list of available link resources can be obtained. For example, a network management protocol (such as SNMP) can be used to send a query command to the management system to obtain relevant link information and compile this information into a list of available link resources.

[0173] Step S422: Select links from the list of available link resources whose current load rate meets the preset load conditions as candidate dedicated links.

[0174] The preset load condition is a range of current load rates pre-set based on actual needs and experience, used to filter out communication links with lighter loads. Candidate dedicated links refer to links selected from the list of available link resources whose current load rates meet the preset load condition. These links can serve as candidate options for allocating dedicated communication links to priority coordinating devices.

[0175] When filtering candidate dedicated links from the list of available link resources, each link in the list is traversed, and its current load rate is checked to see if it is within the preset load condition range. For example, if the preset load condition is that the current load rate is less than 30%, and the list of available link resources contains link 1 (current load rate 20%), link 2 (current load rate 40%), and link 3 (current load rate 15%), then the selected candidate dedicated links are link 1 and link 3.

[0176] Step S423: Based on the physical location distribution of the priority collaborative device pairs, calculate the matching degree between the communication distance between the device pairs and the coverage of the candidate dedicated links.

[0177] The physical location distribution of a priority coordinating device pair refers to the location information of the two devices in the physical space, which can be represented by coordinates or addresses. Communication distance refers to the actual physical distance between the two devices in the priority coordinating device pair, which affects the transmission quality and communication latency of the communication signal. The coverage area of ​​a candidate dedicated link refers to the physical space area that each candidate dedicated link can cover; different types of communication links (such as wired links and wireless links) have different coverage areas. Matching degree refers to the degree of fit between the communication distance between the device pair and the coverage area of ​​the candidate dedicated link; the higher the matching degree, the more suitable the link is as a dedicated communication link for the priority coordinating device pair.

[0178] When calculating the matching degree between the communication distance between device pairs and the coverage of candidate dedicated links, Geographic Information System (GIS) technology or spatial geometric calculation methods can be used. If the physical locations of the preferred cooperating device pairs are represented by coordinates, and the coverage of the candidate dedicated links is represented by polygons, the straight-line distance between the device pairs can be calculated, and it can be determined whether this distance is within the coverage area of ​​the polygon. If it is within the coverage area, the distance between the communication distance between the device pairs and the center of the polygon can be further calculated; the closer the distance, the higher the matching degree.

[0179] Step S424: Select the candidate dedicated link with the best matching degree as the target dedicated link and allocate the corresponding bandwidth capacity to it.

[0180] Optimal matching refers to the link among the candidate dedicated links that best matches the communication distance and communication requirements of the priority cooperating device pair. The target dedicated link is selected from the candidate dedicated links to provide communication services for the priority cooperating device pair. Allocating corresponding bandwidth capacity means allocating appropriate bandwidth resources to the target dedicated link according to the communication requirements of the priority cooperating device pair to ensure efficient and stable communication between the device pairs.

[0181] When selecting the candidate dedicated link with the best matching degree, the matching degree of each candidate dedicated link is compared, and the link with the highest matching degree is selected as the target dedicated link. The matching degree can be quantified into a numerical value, and the optimal link is determined by comparing the magnitude of the numerical values.

[0182] After identifying the target dedicated link, bandwidth capacity is allocated based on the communication needs of the priority coordinating device pair. The communication needs of the priority coordinating device pair can be determined based on factors such as its service type and data transmission volume. For example, if the priority coordinating device pair requires a large amount of real-time data transmission, such as video surveillance data or real-time power system monitoring data, then a larger bandwidth capacity needs to be allocated to it; if it only transmits a small amount of control commands, then a smaller bandwidth capacity can be allocated. This can be achieved by interacting with the communication network management system and sending a bandwidth allocation request to allocate the corresponding bandwidth capacity to the target dedicated link.

[0183] Step S425: Reserve a portion of bandwidth capacity as a backup resource to cope with sudden communication needs of priority cooperating device pairs.

[0184] Backup resources refer to a portion of bandwidth resources reserved when allocating bandwidth capacity for a dedicated link. These resources can provide additional bandwidth support to prioritized coordinating devices in the event of sudden communication demands. Sudden communication demands refer to the need for prioritized coordinating devices to temporarily increase communication bandwidth under certain special circumstances, such as equipment failure recovery or emergency data transmission.

[0185] Maintaining backup resources can improve the reliability and flexibility of communication systems. When allocating bandwidth capacity for a target dedicated link, a certain percentage of bandwidth should be reserved as backup resources based on experience and predictions of the communication needs of priority coordinating devices. For example, 20% of the maximum bandwidth capacity of the target dedicated link can be reserved as backup resources. When priority coordinating devices experience sudden communication demands, additional bandwidth can be dynamically allocated from the backup resources to meet their needs. Simultaneously, after the backup resources are used, timely monitoring and adjustments are necessary to ensure their proper use and recovery.

[0186] Step S426: Record the target dedicated link identifier, allocated bandwidth capacity, and spare resource information into the communication resource allocation scheme.

[0187] Recording the target dedicated link identifier, allocated bandwidth capacity, and reserve resource information in the communication resource allocation scheme is for detailed recording and management of communication resource allocation, facilitating subsequent querying, adjustment, and maintenance. The target dedicated link identifier is information used to uniquely identify the target dedicated link, such as link number and name. Allocated bandwidth capacity refers to the actual amount of bandwidth resource allocated to the target dedicated link. Reserve resource information includes the bandwidth capacity and usage status of reserve resources.

[0188] This information can be recorded using a database or a file. In a database, a table can be created with fields including the target dedicated link identifier, allocated bandwidth capacity, spare resource bandwidth capacity, and spare resource usage. The target dedicated link identifier, allocated bandwidth capacity, and spare resource information are then inserted into the table. In a file, a CSV file format can be used, with each row containing the target dedicated link identifier, allocated bandwidth capacity, and spare resource information, separated by commas. For example, if the target dedicated link identifier is "Link A," the allocated bandwidth capacity is 100Mbps, and the spare resource bandwidth capacity is 20Mbps, it can be recorded in the CSV file as "Link A, 100Mbps, 20Mbps." Summarizing these records forms the detailed information about the target dedicated link in the communication resource allocation scheme.

[0189] Step S430: For device pairs whose coordination score does not reach the preset threshold, a shared communication link is allocated, and their transmission priority in the shared link is dynamically adjusted according to the coordination score.

[0190] A shared communication link is a communication link used by multiple devices, which can improve the utilization of communication resources. For device pairs whose coordination score does not reach a preset threshold, due to their relatively low coordination, there is no need to allocate a dedicated communication link for them; they can share the communication link. Transmission priority refers to the order in which devices transmit data on a shared communication link. Dynamically adjusting the transmission priority based on the coordination score ensures that devices with higher coordination scores can transmit data first on the shared communication link, improving communication efficiency and coordination effectiveness.

[0191] When allocating a shared communication link to a pair of devices that has not reached a preset threshold, a suitable link is selected from the available shared communication links. The link selection can be based on factors such as the physical location of the device pair and its communication needs. When allocating transmission priorities, the coordination score is used as a reference. Device pairs with higher coordination scores have higher transmission priorities on the shared communication link; conversely, device pairs with lower coordination scores have lower transmission priorities. Priority setting requests can be sent to the communication network management system to set corresponding transmission priorities for each device pair. For example, if device pair D has a coordination score of 0.4 and device pair E has a coordination score of 0.5, then device pair E has a higher transmission priority than device pair D on the shared communication link.

[0192] Step S440: Analyze the trend of the collaboration score of each pair of devices in the device collaboration priority sequence. If the collaboration score is on the rise, increase the information interaction frequency; if it is on the fall, decrease the information interaction frequency.

[0193] The trend of the collaboration score refers to how the collaboration score of a device pair changes over time, including upward, downward, and stable trends. Information exchange frequency refers to the frequency of information exchange between device pairs, which affects the collaboration effect and the efficiency of communication resource utilization. When the collaboration score is on an upward trend, it indicates that the collaboration relationship between the device pairs is improving; increasing the information exchange frequency can further promote collaboration and improve the collaboration effect. When the collaboration score is on a downward trend, it indicates that the collaboration relationship between the device pairs may be problematic; reducing the information exchange frequency can reduce unnecessary waste of communication resources.

[0194] Analyzing the changing trends of collaboration scores for each pair of equipment in the equipment collaboration priority sequence can be achieved through time series analysis of historical collaboration scores. For example, methods such as moving averages and exponential smoothing can be used to smooth the collaboration scores, and then the difference between scores at adjacent time points can be calculated to determine the trend. A positive difference indicates an upward trend in the collaboration score; a negative difference indicates a downward trend.

[0195] After determining the trend of the coordination score, the information interaction frequency between the devices is adjusted accordingly. This can be achieved by interacting with the device's communication control system and sending instructions to adjust the frequency. For example, if the coordination score for device F is found to be increasing, its information interaction frequency is increased from once per minute to twice per minute; if the coordination score for device G is found to be decreasing, its information interaction frequency is decreased from twice per minute to once per minute.

[0196] Step S450: Integrate the dedicated communication link allocation rules, the shared communication link priority adjustment rules, and the information exchange frequency dynamic adjustment rules to generate a communication resource allocation scheme that includes specific link identifiers and frequency parameters.

[0197] Dedicated communication link allocation rules refer to the rules and methods for allocating dedicated communication links to priority cooperating devices, including rules for link selection, bandwidth allocation, and reserve of spare resources. Shared communication link priority adjustment rules refer to the rules for adjusting the transmission priority of a device pair in a shared communication link based on its cooperation score. Dynamic adjustment rules for information exchange frequency refer to the rules for adjusting the information exchange frequency of a device pair based on the changing trend of its cooperation score. Integrating these rules forms a complete communication resource allocation scheme, which includes specific link identifiers and frequency parameters, and can guide the communication system to perform accurate resource allocation and management.

[0198] When integrating rules, the allocation of dedicated communication links, priority settings for shared communication links, and adjustments to information exchange frequencies determined in the previous steps are first summarized and organized. Information such as the target dedicated link identifier, allocated bandwidth capacity, backup resource information, transmission priorities of each device pair in the shared communication link, and information exchange frequencies of each device pair are uniformly recorded. This information can be stored using a database or file, forming a communication resource allocation scheme containing specific link identifiers and frequency parameters. For example, a comprehensive data table can be created in the database, with fields including device pair identifier, dedicated link identifier, allocated bandwidth, backup resources, shared link priority, and information exchange frequency, and relevant information can be inserted into the table. In the file, the communication resource allocation information for each device pair can be stored as an object in JSON format.

[0199] Step S500: Execute distributed device communication control operations based on the communication resource allocation scheme, generate a cooperative communication command containing communication link identifier and interaction frequency parameters, and send the cooperative communication command to the corresponding device to realize multi-device cooperative operation.

[0200] Executing distributed device communication control operations based on a communication resource allocation scheme refers to the actual control and management of distributed device communication according to the rules determined in the scheme, such as link allocation, priority settings, and information exchange frequency adjustments. Cooperative communication commands, generated according to the communication resource allocation scheme, contain communication link identifiers and interaction frequency parameters, guiding devices on how to communicate. By issuing cooperative communication commands to the corresponding devices, the devices can perform operations such as selecting communication links and adjusting information exchange frequencies based on the information in the commands, thereby achieving collaborative operation of multiple devices.

[0201] When generating collaborative communication commands, the communication link identifier and information exchange frequency parameters for each device pair are extracted from the communication resource allocation scheme and organized and encoded according to the prescribed command format. The command format can be designed according to the device's communication protocol and system requirements to ensure that the command can be correctly parsed and executed by the device. For example, the command format can be "Device Pair Identifier - Communication Link Identifier - Information Exchange Frequency", such as "Device Pair H - Link B - 3 times per minute".

[0202] Sending collaborative communication commands to corresponding devices can be done via a communication network. Existing communication protocols, such as TCP / IP and UDP, can be used to send commands to the device's communication interface. Upon receiving the collaborative communication command, the device performs corresponding configuration and adjustments based on the information in the command. For example, the device selects the corresponding communication link based on the communication link identifier and adjusts the time interval for sending and receiving information based on the information exchange frequency parameter. In this way, collaborative communication between distributed devices and collaborative operation of multiple devices can be achieved.

[0203] It is understood that the various algorithms involved in the above descriptions of the embodiments of the present invention, such as Euclidean distance algorithm, cosine distance algorithm, normalization algorithm, DBSCAN algorithm, sorting algorithm, etc., can all be obtained from relevant content in the prior art. To save space, they will not be elaborated on in the embodiments of the present invention. In addition, those skilled in the art can supplement the details based on common knowledge in the art when implementing the solutions of the present invention. For example, based on common knowledge in the art, normalization can be used to eliminate dimensional conflicts before feature fusion, interpolation can be used to eliminate dimensional differences, thresholds can be reasonably set in combination with historical data, experience or business scenario requirements, model training can be performed based on general model training methods, the number of layers in the model structure can be set according to actual needs, activation functions can be selected, etc. The present invention will not provide redundant descriptions of overly detailed implementation processes.

[0204] Figure 2 A hardware entity diagram of a computer system provided as an embodiment of the present invention, such as... Figure 2 As shown, the hardware entity of the computer system 1000 includes a processor 1001 and a memory 1002, wherein the memory 1002 stores a computer program that can run on the processor 1001, and the processor 1001 executes the program to implement the steps in the method of any of the above embodiments.

[0205] The memory 1002 stores computer programs that can run on the processor. The memory 1002 is configured to store instructions and applications that can be executed by the processor 1001. It can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) of the processor 1001 and various modules in the computer system 1000. It can be implemented by flash memory or random access memory (RAM).

[0206] When processor 1001 executes a program, it implements the steps of any of the above-mentioned event-triggered communication-based distributed multi-device collaborative methods. Processor 1001 typically controls the overall operation of computer system 1000.

[0207] The above description is merely an embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A distributed multi-device collaboration method based on event-triggered communication, characterized in that, The method comprises: acquiring a real-time state perception data set of a distributed device cluster in a power system, the real-time state perception data set containing operation instruction records, running mode identification and environmental interference detection information of each device; performing device correlation feature analysis processing on the real-time state perception data set to obtain operation synchronization features and environmental interference coupling features between devices; calling a pre-trained collaborative decision-making model to perform collaborative degree evaluation processing on the operation synchronization features and the environmental interference coupling features to generate a device collaborative priority sequence; determining a communication resource allocation scheme according to the device collaborative priority sequence, the communication resource allocation scheme containing selection rules and information interaction frequency adjustment rules of inter-device communication links; performing distributed device communication control operations based on the communication resource allocation scheme to generate collaborative communication instructions containing communication link identification and interaction frequency parameters, and issuing the collaborative communication instructions to corresponding devices to realize multi-device collaborative operation.

2. The distributed multi-device collaboration method based on event-triggered communication according to claim 1, wherein, The device correlation feature analysis processing on the real-time state perception data set to obtain operation synchronization features and environmental interference coupling features between devices comprises: performing time sequence alignment processing on the operation instruction records in the real-time state perception data set to generate a timestamp sequence of each device operation instruction; analyzing the time overlap area of different device operation instructions in the timestamp sequence to extract type matching degree and execution target consistency parameters of operation instructions in the overlap area as operation synchronization features between devices; performing spatial correlation analysis processing on the environmental interference detection information in the real-time state perception data set to identify the interference source distribution range and interference intensity variation trend of the environment in which each device is located; calculating the spatial overlap area and intensity variation correlation parameters of different device environmental interference detection information to generate environmental interference coupling features reflecting the mutual influence degree of environmental interference between devices; inputting the operation synchronization features and the environmental interference coupling features into a feature correlation module for cross-validation processing to screen out an effective correlation feature set that simultaneously satisfies operation synchronization and environmental interference coupling.

3. The distributed multi-device collaboration method based on event-triggered communication according to claim 2, wherein, The time sequence alignment processing on the operation instruction records in the real-time state perception data set to generate a timestamp sequence of each device operation instruction comprises: extracting the instruction trigger time point and the instruction completion time point in each operation instruction record to construct an instruction time interval containing the start time and the end time; performing time offset correction processing on the instruction time interval of each device based on the system global clock to eliminate the deviation of the device local clock from the global clock; arranging the corrected instruction time interval in chronological order to generate an independent operation instruction time axis for each device; performing time point sampling processing on the operation instruction time axis of each device to extract instruction trigger event points on the time axis in units of a preset time interval; converting the instruction trigger event points into discrete data points containing timestamps to generate a timestamp sequence of each device operation instruction after classification and arrangement according to the device identification.

4. The distributed multi-device collaboration method based on event-triggered communication according to claim 2, wherein, The analysis of the time overlap region of different device operation instructions in the timestamp sequence extracts the type matching degree and execution target consistency parameters of the operation instructions in the overlap region as the operation synchronization features between devices, comprising: Selecting the timestamp sequences of any two devices for time overlap detection processing, calculating the proportion of the number of event points in the same time interval of the two timestamp sequences as the time overlap rate; For the device pair with a time overlap rate reaching a preset threshold, extracting the operation instruction types in the overlap time interval, and calculating the proportion of the number of the same type instructions as the type matching degree; Analyzing the execution target description information of each operation instruction in the overlap time interval, and determining the consistency degree parameter of the instruction execution target through semantic similarity calculation; The time overlap rate, type matching degree and execution target consistency degree parameter are weighted and summed to generate a comprehensive synchronization index reflecting the operation synchronization degree between devices; The comprehensive synchronization index is stored in association with the device identifier to form a device operation synchronization feature set containing device pair identifiers and corresponding comprehensive synchronization indexes.

5. The distributed multi-device collaboration method based on event-triggered communication according to claim 2, wherein, The spatial correlation analysis processing of the environmental interference detection information in the real-time state perception data set identifies the interference source distribution range and interference intensity variation trend of the environment where each device is located, comprising: Extracting the interference source location coordinates and interference intensity values in each environmental interference detection information, and constructing interference source feature points containing location coordinates and intensity values; Performing spatial clustering analysis processing on the interference source feature points, identifying interference source aggregation areas with the same interference type, and determining the boundary coordinate range of each aggregation area as the interference source distribution range; Arranging the interference intensity values in the same interference source aggregation area in time sequence to generate sequence data of the interference intensity variation over time; Performing trend fitting processing on the sequence data to calculate the time variation slope and periodic fluctuation amplitude parameters of the interference intensity, generating the interference intensity variation trend reflecting the long-term change direction and short-term fluctuation characteristics of the interference intensity; The interference source distribution range and interference intensity variation trend are stored in association with the device identifier to form the environmental interference feature description corresponding to each device; The spatial overlap region and intensity variation correlation parameter of different device environmental interference detection information are calculated to generate an environmental interference coupling feature reflecting the mutual influence degree of the environmental interference between devices, comprising: Selecting the environmental interference feature description of any two devices, and extracting the boundary coordinates of the interference source distribution range; Calculate the ratio of the spatial intersection area of the two interference source distribution ranges to the area of each distribution range to generate an overlap area proportion parameter reflecting the spatial overlap degree of the interference sources; Extracting the time sequence data of the interference intensity variation trend of the two devices, calculating the correlation parameter of the two time sequences as the intensity variation correlation parameter; Analyzing the correlation between the overlap area proportion parameter and the intensity variation correlation parameter, and constructing an environmental interference coupling degree evaluation function; The environmental interference coupling degree value between devices is calculated through the environmental interference coupling degree evaluation function, and the coupling degree value is stored in association with the device pair identifier to form an environmental interference coupling feature set containing device pair identifiers and corresponding coupling degree values.

6. The distributed multi-device collaboration method based on event-triggered communication according to claim 1, wherein, The call pre-training collaborative decision model evaluates the operation synchronization characteristics between devices and the environment interference coupling characteristics, generates a device collaboration priority sequence, including: The comprehensive synchronization indicators in the operation synchronization characteristics between devices and the coupling degree values in the environment interference coupling characteristics are input into the feature fusion layer of the collaborative decision model for normalization processing to eliminate dimensional differences; The normalized comprehensive synchronization indicators and coupling degree values are cross-correlation analyzed by the correlation analysis layer of the collaborative decision model to generate a joint feature vector reflecting the collaborative effect of the operation between devices and the environment interference; The joint feature vector is weighted and summed by the evaluation calculation layer of the collaborative decision model, wherein the weights of the operation synchronization indicators and the weights of the environment interference coupling degree are dynamically adjusted according to historical collaborative effect data; The weighted sum result is taken as the collaboration score value between devices, and the device pairs are sorted in descending order of the collaboration score value; According to the sorting result, a device collaboration priority sequence containing device pair identification and corresponding collaboration score value is generated.

7. The distributed multi-device collaboration method based on event-triggered communication according to claim 6, wherein, The cross-correlation analysis processing of the normalized comprehensive synchronization indicators and coupling degree values by the correlation analysis layer of the collaborative decision model generates a joint feature vector reflecting the collaborative effect of the operation between devices and the environment interference, including: The normalized comprehensive synchronization indicators and coupling degree values are differentially processed, and the absolute value of the difference is taken as the collaborative effect difference parameter; The time series data of the comprehensive synchronization indicators and the coupling degree values are extracted, and the covariance value of the two is taken as the collaborative effect correlation parameter; The collaborative effect difference parameter and the collaborative effect correlation parameter are dimensionally expanded to generate a two-dimensional feature vector containing difference dimension and correlation dimension; The two-dimensional feature vector is subjected to principal component analysis processing, and the principal component that can explain most of the data variance is extracted as the core collaborative feature; The core collaborative feature is spliced with the original comprehensive synchronization indicators and coupling degree values to generate a joint feature vector containing multi-dimensional information.

8. The distributed multi-device collaboration method based on event-triggered communication according to claim 1, wherein, The communication resource allocation scheme is determined according to the device collaboration priority sequence, and the communication resource allocation scheme contains the selection rules of the inter-device communication link and the information interaction frequency adjustment rules, including: The device pairs with collaboration score values reaching a preset threshold in the device collaboration priority sequence are extracted as priority collaborative device pairs; The priority collaborative device pairs are allocated with dedicated communication links, and the bandwidth resources of the dedicated communication links are prioritized over the shared communication links of other device pairs; For device pairs with collaboration score values not reaching the preset threshold, shared communication links are allocated, and their transmission priority in the shared link is dynamically adjusted according to the collaboration score value; The collaboration score value change trend of each device pair in the device collaboration priority sequence is analyzed, if the collaboration score value shows an upward trend, the information interaction frequency is increased, and if the collaboration score value shows a downward trend, the information interaction frequency is reduced; The dedicated communication link allocation rule, the shared communication link priority adjustment rule and the information interaction frequency dynamic adjustment rule are integrated to generate a communication resource allocation scheme containing specific link identification and frequency parameters.

9. The distributed multi-device collaboration method based on event-triggered communication according to claim 8, wherein, The dedicated communication link allocated to the priority cooperative device pair has bandwidth resources that are prior to shared communication links of other device pairs, and the method comprises the following steps: Obtaining a list of available link resources in a power system communication network, wherein the list of available link resources contains link identification, maximum bandwidth capacity and current load rate; Filtering links with current load rates meeting preset load conditions from the list of available link resources as candidate dedicated links; Calculating the matching degree of communication distance between device pairs and coverage range of the candidate dedicated links according to the physical position distribution of the priority cooperative device pair; Selecting the candidate dedicated link with the optimal matching degree as a target dedicated link and allocating corresponding bandwidth capacity to the target dedicated link; Reserving part of the bandwidth capacity as backup resources for coping with burst communication demands of the priority cooperative device pair; Recording the target dedicated link identification, allocated bandwidth capacity and backup resource information into a communication resource allocation scheme.

10. A computer system comprising a memory and a processor, said memory storing a computer program operable on the processor, characterised in that, The processor implements the steps in the method of any one of claims 1 to 9 when executing the program.

Images