A high-compatibility smart park device coordination management method and system

Abstract

The application relates to the technical field of smart park equipment management, in particular to a high-compatibility smart park equipment collaborative management method and system, which comprises collecting equipment operation data through a sensor network and constructing a multi-level collaborative framework, combining hierarchical clustering and a self-adaptive optimization model to generate a dynamic power distribution scheme, and continuously optimizing the collaborative strategy through a feedback loop mechanism. The application can realize fine management of the equipment operation state, dynamically adjust power distribution, guarantee efficient operation and resource utilization balance of the park equipment under complex scenes, and provide flexible and reliable equipment management capability for the smart park.

Description

Technical Field

[0001] This invention belongs to the field of smart park equipment management technology, specifically a highly compatible smart park equipment collaborative management method and system. Background Technology

[0002] With the rapid development of smart parks, equipment management is playing an increasingly important role in improving park operational efficiency and resource utilization. Currently, equipment management methods in smart parks are mainly based on a broad, system-level approach, focusing on overall load balancing or macroscopic operational status control, while lacking detailed insights into equipment operating status and the ability to dynamically adjust. This management model typically suffers from insufficient granularity, making it difficult to accurately respond to the personalized needs of different equipment in specific scenarios. For example, in power distribution scenarios, existing methods often only focus on balancing the overall power load, ignoring the operational characteristics and demand differences of specific equipment or circuits at different times, leading to frequent instances of low equipment efficiency or resource waste. Furthermore, due to the lack of multi-level collaborative mechanisms, the flexibility and efficiency of existing technologies in complex scenarios are significantly limited, making it difficult to meet the urgent needs of smart parks for refined management and intelligent collaboration.

[0003] Therefore, how to achieve comprehensive perception, dynamic adjustment, and multi-level collaborative optimization of the operational status of park equipment through technological innovation has become an urgent technical challenge. Developing a highly compatible smart park equipment collaborative management method and system can not only make up for the shortcomings of existing technologies in terms of management granularity and dynamic adjustment capabilities, but also provide smart parks with a more flexible, efficient, and intelligent equipment management solution, which has significant practical significance and application value. Summary of the Invention

[0004] The purpose of this invention is to overcome the above-mentioned shortcomings and provide a highly compatible smart park equipment collaborative management method and system. The smart park equipment collaborative management method includes: collecting real-time operating data from park equipment through a sensor network, including power load and environmental parameters; processing the data using a data aggregation method to obtain equipment state vectors; grouping the data according to the equipment state vectors using a hierarchical clustering algorithm, and dividing the grouping results into system-level, region-level, and equipment-level granular levels to determine a multi-level collaborative framework; obtaining local precise requirements in the multi-level collaborative framework; if the local precise requirements exceed a preset threshold, triggering a dynamic adjustment signal to determine whether cross-level linkage is needed; extracting collaborative requirements from the dynamic adjustment signal, generating inter-equipment collaborative strategies using an adaptive optimization model, and obtaining an adjusted power allocation scheme through simulation training of the model; analyzing the global overall impact of the adjusted power allocation scheme; if the global overall impact is lower than a preset threshold, distributing the scheme to the corresponding equipment loops to obtain an updated operating configuration; monitoring resource usage changes through the updated operating configuration, comparing the changes with the dynamic requirements using a feedback loop mechanism to determine the optimization direction of the collaborative mechanism; generating a control command sequence from the optimization direction of the collaborative mechanism, and executing the sequence in real time among the equipment to obtain the overall stable operating state of the park.

[0005] Furthermore, the method for constructing the multi-level collaborative framework includes: establishing a multi-dimensional space with each device type as each dimension; for any device, mapping its operational data in different time periods to the multi-dimensional space and performing clustering to obtain operational behavior clusters; determining a preferred operating area in the multi-dimensional space based on the preset ideal range of the device under each environmental parameter; obtaining the device's adaptability in each time period based on the difference between the center point position deviation and the corresponding operating efficiency between the operational behavior clusters in which the device is located and the preferred operating area; using the product of the device's adaptability in each time period and the corresponding operating efficiency as an adjustment value; and using the sum of the device's adjustment value and the corresponding operating efficiency in each time period as the device's adaptability efficiency in each time period.

[0006] Furthermore, the method for obtaining the local precise demand includes: for any device in any time period, sorting the power load of all time periods before the current time period by time sequence to obtain the load sequence of the device; performing fluctuation analysis on the load sequence of the device to obtain a fluctuation sequence; when the value of the fluctuation value in the fluctuation sequence after normalization is greater than a preset screening threshold, the corresponding fluctuation value is taken as a high fluctuation value; the difference between the maximum load in all time periods of the device's operation and the load in the current time period is taken as the relative demand of the device in the current time period; combining the ratio between the number of all high fluctuation values ​​of the device and the total number of time periods, as well as the sum of all high fluctuation values ​​and the relative demand of the current time period, to obtain the local precise demand of the device in the current time period.

[0007] Furthermore, the method for triggering the dynamic adjustment signal includes: mapping the local precise demand of each device in the current time period to a value that is positively correlated, and using it as the trigger intensity of each device in the corresponding time period; if the trigger intensity exceeds a preset threshold, a dynamic adjustment signal is generated, and it is determined whether cross-level linkage is required.

[0008] Furthermore, the determination of whether cross-level linkage is required includes: triggering device-level linkage when the device's local precision requirement Q meets the first condition; triggering region-level linkage when the device's local precision requirement Q meets the second condition; and triggering system-level linkage when the device's local precision requirement Q meets the third condition.

[0009] Furthermore, the method for obtaining the adjusted power allocation scheme includes: before each time period, predicting the load distribution of each device in the time sequence of the detection time period, and adjusting it through local precise demand to obtain the predicted load for each time period; in each time period, multiplying the value of the positive correlation mapping of the local precise demand of each device with the predicted load as the power allocation weight of each device in each time period; and combining the power allocation weight with the overall planning influence to obtain the adjusted power allocation scheme.

[0010] Furthermore, the method for obtaining the overall coordination impact includes: obtaining the balance difference degree of each time period based on the uniformity of the power allocation weight of each device in each time period; obtaining the balance difference growth degree of the current time period based on the changes in the balance difference degree of the time periods in the local range before the current time period; and obtaining the overall coordination impact of the current time period by combining the difference between the balance difference degree of the current time period and the previous time period, as well as the balance difference growth degree.

[0011] Furthermore, the method for obtaining the balance difference degree includes: for any time period, calculating the average power allocation weight of all devices in that time period as the weight average; calculating the difference between the power allocation weight of each device and the weight average in that time period, and then summing all the differences as the balance difference degree of that time period.

[0012] The method for obtaining the equilibrium difference growth rate includes: counting the number of time periods with a lower equilibrium difference rate than the previous time period within a local range before the current time period, and obtaining the equilibrium difference growth rate of the current time period based on the proportion of the number of time periods in the total number of time periods within the local range.

[0013] This invention also provides a highly compatible smart park equipment collaborative management system, comprising:

[0014] The data acquisition module is used to collect real-time operating data from park equipment through a sensor network, including power load and environmental parameters, and to process the data using a data aggregation method to obtain equipment state vectors.

[0015] The collaborative framework construction module is used to group data based on device state vectors using a hierarchical clustering algorithm, and to divide the grouping results into system-level, region-level, and device-level granular levels to determine a multi-level collaborative framework.

[0016] The dynamic adjustment module is used to obtain the local precise requirements in the multi-level collaborative framework. If the local precise requirements exceed the preset threshold, the dynamic adjustment signal is triggered to determine whether cross-level linkage is required.

[0017] The power allocation module is used to extract cooperation requirements from dynamic adjustment signals, generate inter-device cooperation strategies using an adaptive optimization model, and obtain the adjusted power allocation scheme by training the model through simulation.

[0018] The global coordination module is used to analyze the global coordination impact of the adjusted power allocation scheme. If the global coordination impact is lower than the preset threshold, the scheme is distributed to the corresponding equipment loop to obtain the updated operating configuration.

[0019] The feedback optimization module is used to monitor changes in resource usage through updated runtime configurations, and uses a feedback loop mechanism to compare the degree of matching between changes and dynamic requirements to determine the optimization direction of the collaboration mechanism.

[0020] The control execution module is used to generate a sequence of control instructions from the optimization direction of the collaborative mechanism, and to execute the sequence in real time among devices to obtain the overall stable operation status of the park.

[0021] Compared with existing technologies, this invention has the following advantages: It constructs a multi-level collaborative framework at the system, regional, and device levels, combining device operation data clustering with environmental parameters to quantify adaptation efficiency and accurately characterize device status. Simultaneously, it quantifies precise local requirements through a multi-dimensional model, triggering different levels of linkage in a tiered manner. Compared to existing single static threshold management, it can accurately match the personalized needs of devices, avoid over- or under-adjustment, significantly reduce the misadjustment rate, and promote a shift from extensive to precise device management.

[0022] Furthermore, in the power allocation stage, load forecasting and local demand are combined to determine weights, and the global impact is analyzed through "balance difference degree + balance difference growth degree" to avoid global imbalance caused by local optimization. With the addition of a feedback loop mechanism and flexible and adjustable linkage thresholds, it can adapt to complex scenarios such as morning and evening peak hours and equipment failures in the park, reduce operational risks, improve equipment efficiency and resource utilization, ensure the efficient and stable operation of park equipment, and provide smart parks with more flexible and reliable equipment management capabilities. Attached Figure Description

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

[0024] Figure 1 A flowchart of a smart park equipment collaborative management method provided in an embodiment of the present invention. Detailed Implementation

[0025] This invention provides a highly compatible smart park equipment collaborative management method and system. Its core lies in achieving refined management of the park equipment's operating status through a multi-layered collaborative framework, and dynamically adjusting the power allocation scheme using an adaptive optimization model, ultimately ensuring efficient operation and resource utilization balance of park equipment in complex scenarios. The following is in conjunction with the appendix... Figure 1 The technical solution of the present invention will be described in detail with specific embodiments.

[0026] First, such as Figure 1As shown, in practical applications, the specific implementation of this invention focuses on monitoring power load and environmental parameters in a smart park, collecting real-time operational data through a sensor network. This data includes, but is not limited to, environmental parameters such as power load, temperature, humidity, and light intensity. The data acquisition module is responsible for obtaining this data from various devices and processing it using data aggregation methods to generate device state vectors. These device state vectors are the foundation for subsequent analysis, and their construction process is as follows: For each device, the collected multidimensional data is arranged according to a time series, and the comprehensive state value of the device within a certain time period is calculated using a weighted average or sliding window algorithm. For example, if the power load of a device within a certain time period is L1, L2, L3, and the environmental parameters are T1, T2, T3, then the device state vector can be expressed as V=[w1L1+w2T1,w1L2+w2T2,w1L3+w2T3], where w1 and w2 are the weighting coefficients of the power load and environmental parameters, respectively, and can be adjusted according to actual conditions.

[0027] Next, the collaborative framework construction module applies a hierarchical clustering algorithm to group the data based on the device state vectors, dividing it into system-level, region-level, and device-level granular levels to determine the multi-level collaborative framework. Specifically, a multi-dimensional space is first established for each device type, with different dimensions for each device type. For example, air conditioning equipment, lighting equipment, and security equipment correspond to different dimensions. For any given device, its operating data over different time periods is mapped to the multi-dimensional space and clustered to obtain clusters of operating behaviors. Assuming that device A's operating data over a certain time period is [X1, X2, X3], its position in the multi-dimensional space can be represented by the formula P = (X1, X2, X3). The clustering algorithm uses common methods such as K-means or DBSCAN to group devices with similar operating behaviors into the same cluster. Simultaneously, based on the preset ideal range of the device under each environmental parameter, a preferred operating area is determined in the multi-dimensional space. The center point C of the preferred operating area can be represented by the formula C = (C1, C2, C3), where C1, C2, and C3 are the ideal values ​​for each dimension. Subsequently, the distance between the center point of each operational behavior cluster and the center point of the preferred operational area is calculated as the operational impact degree D, with the formula D=sqrt((C1-P1)^2+(C2-P2)^2+(C3-P3)^2). Furthermore, the difference in equipment operating efficiency between the center point of each operational behavior cluster and the center point of the preferred operational area is used as the performance impact degree E, with the formula E=abs(Ec-Ep), where Ec and Ep are the efficiency values ​​of the preferred and actual operational areas, respectively. Combining the operational impact degree D and the performance impact degree E, a weighted summation is used to obtain the fit degree F, i.e., F=αD+βE, where α and β are weight coefficients. α can be 0.6 (operational impact degree weight), and β can be 0.4 (performance impact degree weight), which can be determined through regression analysis of historical equipment operating data. Finally, the product of the fit degree F and the corresponding operational efficiency R is used as the adjustment value G, i.e. The sum of the adjustment value G and the operating efficiency R is then used as the adaptation efficiency H of the equipment for each time period, i.e., H = G + R. Through the above steps, the operating status of the equipment in different time periods can be quantified, providing a basis for subsequent dynamic adjustments.

[0028] In the dynamic adjustment module, obtaining precise local demand is a key step. For any device in any time period, the power load of all time periods preceding the current time period is sorted chronologically to obtain the load sequence S. For example, if the power load of a device in three time periods is L1, L2, and L3, then the load sequence S = [L1, L2, L3]. Fluctuation analysis is performed on this load sequence to obtain the fluctuation sequence V. The fluctuation value Vi can be calculated using the formula Vi = abs(Si - Si-1), where Si and Si-1 are the load values ​​in the i-th and (i-1)-th time periods, respectively. When the normalized value of a fluctuation value in the fluctuation sequence is greater than a preset screening threshold, the corresponding fluctuation value is designated as a high fluctuation value. Assume the normalization formula is Vn = Vi / max(V), where max(V) is the maximum value in the fluctuation sequence. If Vn > T0, where T0 is the screening threshold, then Vi is marked as a high fluctuation value. T0 can be set according to the statistical characteristics of load fluctuations of equipment in the park. Simultaneously, the difference between the maximum load across all time periods and the load during the current time period is used as the relative demand level N, calculated as N = max(L) - Li, where max(L) is the maximum load value across all time periods, and Li is the load value during the current time period. Combining the ratio of the number of high-fluctuation values ​​to the total number of high-fluctuation values ​​across time periods, the sum of all high-fluctuation values, and the relative demand level N, a weighted summation is used to obtain the local precise demand Q, i.e. Where H represents the number of high-fluctuation values, T represents the total number of values ​​in the time period, and γ, δ, and ε are weighting coefficients. For example, weighting coefficients γ, δ, and ε can be set to 0.3, 0.4, and 0.3 respectively, and can be adjusted according to the equipment type. If the local precise demand Q exceeds the preset threshold, a dynamic adjustment signal is triggered, and it is determined whether cross-level linkage is needed. The preset threshold is set based on the load sensitivity of the park's equipment; for example, when the power load fluctuation is greater than 10%, the trigger strength threshold is set to 0.5.

[0029] Specifically, the methods for determining whether cross-level collaboration is needed include the following:

[0030] When the local precise demand Q of a single device satisfies Q1≤Q<Q2, only device-level linkage is triggered, where Q1 is the preset threshold for triggering the dynamic adjustment signal, and Q2=a×Q1, where a is a constant greater than 1. That is, the demand is met by adjusting the device's own operating parameters, such as adjusting power output or switching operating modes, without involving regional or system-level resource scheduling. For example, if Q1=0.5 (preset threshold), a=1.2, and the local precise demand Q of a certain lighting device is 0.6 (within the range of 0.5≤0.6<0.6), then only the brightness level of that lighting device needs to be adjusted, without needing to link other lighting devices in the same area.

[0031] When the local precise demand Q of a single device satisfies: Q2≤Q<Q3, or Q≥Q2 for two or more devices in the same area, a regional-level linkage is triggered, where Q3=b×Q1, and b is a constant greater than a. This involves scheduling resources of similar or complementary devices within the area, such as load sharing for air conditioning equipment and power circuits, while simultaneously feeding back to the system-level framework without consuming system-level global resources. For example, if Q1=0.5, Q2=0.6, a=1.2, b=1.5, then Q3=0.75. If the local precise demands Q of two air conditioners in an office area are 0.65 and 0.7 respectively, a regional-level linkage is triggered, putting one idle standby air conditioner in the area into operation to share the load of the two high-demand air conditioners and maintain a stable total cooling capacity within the area.

[0032] When the Q of a single device is greater than or equal to Q3, or the Q of three or more devices in the same area is greater than or equal to Q2, or when devices with Q greater than or equal to Q2 appear in two or more areas, a system-level linkage is triggered. This involves scheduling global resources within the park, such as power allocation of the park's total power distribution network, support scheduling for devices in different areas, and coordinated charging and discharging of energy storage systems. Simultaneously, a system-level emergency plan is activated, prioritizing resource supply for critical equipment (security, emergency lighting). For example, if two air conditioners in areas A and three in areas B of a park have Q greater than or equal to 0.6 (Q1=0.5, Q2=0.6), a system-level linkage is triggered. This connects the park's energy storage system to the power circuits of areas A and B, while simultaneously reducing the power of non-critical equipment (such as landscape lighting) to ensure the power supply for the air conditioning equipment.

[0033] It should be noted that the proportional coefficients 'a' and 'b' used to divide the threshold intervals of the linkage levels are as follows: 'a' is the threshold division coefficient between device-level linkage and region-level linkage, and 'b' is the threshold division coefficient between region-level linkage and system-level linkage. Both must satisfy the basic constraint that 1 < a < b, ensuring that the threshold intervals for device-level, region-level, and system-level linkages do not overlap and can fully cover the value range of all possible local precise demands Q of the equipment, avoiding missed demands or repeated triggering. The specific values ​​of 'a' and 'b' need to be determined comprehensively based on the equipment type, regional load density, and equipment operational sensitivity of the smart park: For precision equipment (such as park data center servers and laboratory testing equipment), load fluctuations have a significant impact on operational stability, requiring a narrower threshold interval for the linkage levels, with 'a' ranging from 1.1 to 1.3 and 'b' ranging from 1.4 to 1.6; for ordinary equipment (such as park lighting equipment and public area air conditioning), load fluctuation tolerance is higher, allowing for a wider threshold interval, with 'a' ranging from 1.3 to 1.5 and 'b' ranging from 1.6 to 1.8. In high-load-density areas (such as office buildings and production workshops in the park), there are many devices and high load correlation. Precise division of linkage levels is necessary to avoid resource scheduling conflicts. The value of 'a' should range from 1.2 to 1.4, and the value of 'b' should range from 1.5 to 1.7. In low-load-density areas (such as green belts and parking lots in the park), devices are dispersed and loads are highly independent. The value of 'a' can be relaxed to 1.4 to 1.6, and the value of 'b' can be relaxed to 1.7 to 1.9. For devices highly sensitive to power supply (such as medical equipment in a medical park and security monitoring systems in the park), rapid response to load changes is required. The value of 'a' should be close to 1.1 to 1.2, and the value of 'b' should be close to 1.4 to 1.5. For devices less sensitive to power supply (such as landscape fountains and background music systems in the park), the value of 'a' can be close to 1.5 to 1.6, and the value of 'b' close to 1.8 to 1.9.

[0034] The core of the dynamically adjusted signal triggering method lies in using the value of a positive correlation mapping between the local precise demand of each device in the current time period and the trigger strength I, as shown in the formula: Where k is the mapping coefficient, and if k is 1.5, it can be determined by the slope of the fitting curve between trigger strength and device response efficiency. If the trigger strength I exceeds a preset threshold, a dynamic adjustment signal is generated. At this time, the power allocation module extracts the cooperation requirements from the dynamic adjustment signal and uses an adaptive optimization model to generate an inter-device cooperation strategy. The core objective of the adaptive optimization model based on a BP neural network is to minimize the power allocation deviation while satisfying the dynamic requirements. Assuming the predicted load is P and the local accurate requirement is Q, the power allocation weight W can be obtained by formula... Calculation. The power allocation weights are combined with the overall planning impact to obtain the adjusted power allocation scheme. The overall planning module is responsible for analyzing the overall planning impact of the power allocation scheme, with its core indicators being the balance difference degree and the balance difference growth rate. The balance difference degree is calculated as follows: First, calculate the mean M of the power allocation weights of all devices in each time period, i.e., M = sum(W) / N, where N is the total number of devices; then calculate the difference d between the power allocation weight of each device and the mean, i.e., d = abs(Wi - M), and use the sum of all differences as the balance difference degree Dg, i.e., Dg = sum(d). The balance difference growth rate is calculated as follows: In the time periods within the local range before the current time period, count the number C of time periods where the balance difference degree is less than the previous time period, and calculate its proportion R, i.e., R = C / Tg, where Tg is the total number of time periods within the local range. Combining the changes in the balance difference degree and the balance difference growth rate, the formula is used to... Calculate the overall impact G, where ΔD is the difference in equilibrium difference between the current time period and the previous time period, and λ is the weighting coefficient. If the overall impact is lower than a preset threshold, the execution plan is distributed to the corresponding equipment loop, resulting in the updated operating configuration.

[0035] The feedback optimization module monitors resource usage changes through updated operational configurations and uses a feedback loop mechanism to compare the changes with dynamic demand, determining the optimization direction of the collaborative mechanism. The control execution module generates a sequence of control commands from the optimization direction of the collaborative mechanism and executes these commands in real-time across devices to achieve a stable overall operating status for the park. For example, if adjusting the power allocation scheme of a device leads to increased load fluctuations, the feedback optimization module will reassess the precise local demand and generate a new optimization direction. The control execution module then generates control commands based on this optimization direction, such as adjusting the device's operating mode or power output, to ensure the overall operating status of the park's devices stabilizes.

[0036] In summary, this invention achieves refined management of equipment operating status through a multi-layered collaborative framework, dynamically adjusts power allocation schemes using an adaptive optimization model, and continuously optimizes collaborative strategies through a feedback loop mechanism, providing smart parks with more flexible and reliable equipment management capabilities. Through the specific implementation methods described above, this invention can effectively address the equipment management needs in complex smart park scenarios, improving resource utilization efficiency and operational stability.

[0037] The above description is only a preferred embodiment of the present invention. Therefore, any equivalent changes or modifications made to the structure, features and principles described in the claims of this patent application are included within the protection scope of this patent application.

Claims

1. A highly compatible smart park equipment collaborative management method, characterized in that, The method includes: Real-time operating data, including power load and environmental parameters, is collected from equipment in the park through a sensor network. The data is then processed using a data aggregation method to obtain equipment state vectors. Based on the device state vector, a hierarchical clustering algorithm is applied to group the data, grouping devices with similar operating behaviors into the same cluster. The grouping results are then divided into system-level, region-level, and device-level granular levels to determine a multi-level collaborative framework. The construction method of the multi-level collaborative framework includes: establishing a multi-dimensional space with each device type as each dimension; for any device, mapping its operating data in different time periods to the multi-dimensional space and performing clustering to obtain operating behavior clusters. The system acquires precise local demand within a multi-layered collaborative framework. If the precise local demand exceeds a preset threshold, a dynamic adjustment signal is triggered to determine whether cross-layered linkage is necessary. The method for acquiring precise local demand includes: for any device and any time period, sorting the power load of all time periods preceding the current time period in chronological order to obtain the device's load sequence; performing fluctuation analysis on the device's load sequence to obtain a fluctuation sequence; when the normalized value of the fluctuation value in the fluctuation sequence is greater than a preset screening threshold, the corresponding fluctuation value is designated as a high fluctuation value; the difference between the maximum load in all time periods of the device's operation and the load in the current time period is used as the relative demand of the device in that time period; combining the ratio of the number of all high fluctuation values ​​of the device to the total number of time periods, the sum of all high fluctuation values, and the relative demand of the time period, the precise local demand of the device in that time period is obtained. The determination of whether cross-level linkage is needed includes: when the local precise demand Q of a device meets the first condition, triggering device-level linkage and adjusting the device's own operating parameters to meet the demand; when the local precise demand Q of a device meets the second condition, triggering region-level linkage and scheduling resources of devices of the same or complementary types within the region; when the local precise demand Q of a device meets the third condition, triggering system-level linkage, scheduling global resources of the park, and activating the system-level emergency plan. The collaboration requirements are extracted from the dynamic adjustment signal, an adaptive optimization model is used to generate the inter-device collaboration strategy, and the model is trained by simulation to obtain the adjusted power allocation scheme. The overall impact of the adjusted power allocation scheme is analyzed. If the overall impact is lower than the preset threshold, the scheme is distributed to the corresponding equipment loops to obtain the updated operating configuration. By monitoring changes in resource usage through updated runtime configurations, a feedback loop mechanism is used to compare the degree of matching between changes and dynamic requirements, and to determine the optimization direction of the collaboration mechanism. A sequence of control commands is generated from the optimization direction of the collaborative mechanism, and the sequence is executed in real time between devices to obtain the overall stable operation status of the park.

2. The highly compatible smart park equipment collaborative management method according to claim 1, characterized in that, The method for constructing the multi-level collaborative framework also includes: Based on the preset ideal range of the equipment under each environmental parameter, the preferred operating area is determined in a multi-dimensional space; Between the operating behavior clusters and the preferred operating areas of the device in each time period, the adaptability of the device in each time period is obtained based on the deviation of the center point position and the difference in the operating efficiency corresponding to the center point. The product of the device's adaptability and its corresponding operating efficiency for each time period is used as the adjustment value; the sum of the adjustment value and the corresponding operating efficiency for each time period is used as the device's adaptability efficiency for each time period.

3. The highly compatible smart park equipment collaborative management method according to claim 1, characterized in that, The triggering method for the dynamic adjustment signal includes: The value of the local precise demand of each device in the current time period is positively correlated and used as the trigger intensity of each device in the corresponding time period; If the trigger strength exceeds the preset threshold, a dynamic adjustment signal is generated, and it is determined whether cross-level linkage is required.

4. The highly compatible smart park equipment collaborative management method according to claim 1, characterized in that, The method for obtaining the adjusted power allocation scheme includes: Before each time period, the load distribution of each device in the time sequence of the detection time period is predicted, and adjusted by local precise demand to obtain the predicted load for each time period; At each time period, the product of the positively correlated value of the local precise demand of each device and the predicted load is used as the power allocation weight for each device at each time period. By combining power allocation weights with overall strategic considerations, an adjusted power allocation scheme is obtained.

5. The highly compatible smart park equipment collaborative management method according to claim 1, characterized in that, The methods for obtaining the overall planning impact include: The balance difference degree for each time period is obtained based on the uniformity of the power allocation weight of each device in each time period. Based on the changes in the equilibrium difference degree within a local range before the current time period, the equilibrium difference growth rate of the current time period is obtained. By combining the difference in equilibrium difference between the current time period and the previous time period, as well as the growth rate of equilibrium difference, the overall impact of the current time period can be obtained.

6. The highly compatible smart park equipment collaborative management method according to claim 5, characterized in that, The method for obtaining the equilibrium difference degree includes: For any given time period, calculate the average power allocation weight of all devices during that time period, and use it as the average weight. After calculating the difference between the power allocation weight and the weight average of each device during the time period, the sum of all differences is taken as the balance difference degree for that time period.

7. The highly compatible smart park equipment collaborative management method according to claim 5, characterized in that, The method for obtaining the equilibrium difference growth rate includes: Within a local range preceding the current time period, the number of time periods where the statistical equilibrium difference is less than that of the previous time period is determined. Based on the proportion of this number to the total number of time periods within the local range, the equilibrium difference growth rate of the current time period is obtained.

8. A highly compatible smart park equipment collaborative management system for implementing the smart park equipment collaborative management method according to any one of claims 1 to 7, characterized in that, include: The data acquisition module is used to collect real-time operating data from the park equipment through a sensor network, including power load and environmental parameters, and to process the data using a data aggregation method to obtain the equipment state vector. The collaborative framework construction module is used to group data based on device state vectors using a hierarchical clustering algorithm, and to divide the grouping results into system-level, region-level, and device-level granular levels to determine a multi-level collaborative framework. The dynamic adjustment module is used to obtain the local precise requirements in the multi-level collaborative framework. If the local precise requirements exceed the preset threshold, the dynamic adjustment signal is triggered to determine whether cross-level linkage is required. The power allocation module is used to extract cooperation requirements from dynamic adjustment signals, generate inter-device cooperation strategies using an adaptive optimization model, and obtain the adjusted power allocation scheme by training the model through simulation. The global coordination module is used to analyze the global coordination impact of the adjusted power allocation scheme. If the global coordination impact is lower than the preset threshold, the scheme is distributed to the corresponding equipment loop to obtain the updated operating configuration. The feedback optimization module is used to monitor changes in resource usage through updated runtime configurations, and uses a feedback loop mechanism to compare the degree of matching between changes and dynamic requirements to determine the optimization direction of the collaboration mechanism. The control execution module is used to generate a sequence of control instructions from the optimization direction of the collaborative mechanism, and to execute the sequence in real time among devices to obtain the overall stable operation status of the park.

Images