An ai intelligent control cabinet distributed control system and method

Abstract

This invention belongs to the field of distributed control technology. It discloses a distributed control system and method for AI smart control cabinets, comprising: acquiring operating status data and control task data; constructing a task priority vector for each smart control cabinet in each control cycle; generating a global task conflict graph based on the task priority vectors of all smart control cabinets in the same control cycle; obtaining the task conflict probability and task execution order of each smart control cabinet in the same control cycle according to the global task conflict graph; adjusting the control task execution strategy of each smart control cabinet based on the task conflict probability and task execution order to obtain an optimized control task sequence for each smart control cabinet; and controlling the distributed collaborative operation of each smart control cabinet in the next control cycle according to the optimized control task sequence, effectively balancing the overall operating efficiency and conflict occurrence rate of the distributed system.

Description

Technical Field

[0001] This invention relates to the field of distributed control technology, and more specifically, to a distributed control system and method for an AI-powered smart control cabinet. Background Technology

[0002] As core equipment in power systems, responsible for key functions such as distribution automation, load control, and protection coordination, the technological evolution of intelligent control cabinets is closely linked to the modernization of the power grid. In the current construction of smart grids, with the continuous deepening of ultra-high voltage transmission, large-scale power grid interconnection, and the intelligent construction of distribution networks, traditional single-function distribution control cabinets have evolved into intelligent power control devices integrating remote measurement and control, relay protection, fault diagnosis, and other functions. In the modern power grid architecture, control cabinets have gradually shifted from their original independent operation mode to a distributed collaborative system, forming a hierarchical distributed control system covering the entire process of power generation, transmission, substation, distribution, and consumption. However, with the widespread application of new technologies such as large-scale grid connection of new energy sources, load-side response, microgrid clusters, and flexible DC transmission, traditional distributed control cabinet systems face severe challenges such as insufficient real-time performance, inadequate coordination, and low levels of intelligence.

[0003] Specifically, in large-scale regional power distribution networks, intelligent control cabinets generally operate in a "single-point response" mode, lacking a coordinated linkage mechanism. This results in an inability to flexibly allocate resources during peak electricity demand periods or sudden load changes, leading to localized overloads or even cascading failures. Especially in modern power grids with large-scale integration of renewable energy, the intermittency and volatility of new energy sources such as wind and solar power render traditional control systems inadequate, unable to accurately predict and smooth power fluctuations, causing degraded power quality and increased system stability risks. Power dispatch centers lack unified coordination methods for control cabinets scattered across various substations. When grid disturbances or faults occur, the protection actions between control cabinets lack coordination, easily leading to protection coordination errors and expanding the scope of the fault. The fixed priority response mechanism used in traditional power control systems cannot cope with increasingly complex grid operation scenarios and is slow to respond to new business demands such as demand-side response and distributed power dispatch. Furthermore, the status monitoring and fault early warning of power equipment rely on the independent judgment of each control cabinet, lacking data sharing and joint analysis capabilities. This makes it difficult to detect equipment hazards in a timely manner, resulting in low maintenance efficiency and increased power outage risks and economic losses. In smart microgrids and industrial park power supply systems, power dispatch conflicts between multiple control cabinets occur frequently. However, existing technologies lack intelligent conflict solutions, often leading to uneven power distribution, energy waste, or fluctuations in power quality.

[0004] In view of this, the present invention proposes an AI-powered intelligent control cabinet distributed control system and method to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: a distributed control method for an AI smart control cabinet, comprising:

[0006] Obtain the operating status data and control task data of each smart control cabinet in each control cycle; construct the task priority vector of each smart control cabinet in each control cycle based on the operating status data and the control task data;

[0007] A global task conflict diagram is generated based on the task priority vector of all intelligent control cabinets within the same control cycle.

[0008] Based on the global task conflict diagram, obtain the task conflict probability and task execution order of each smart control cabinet within the same control cycle;

[0009] Based on the task conflict probability and the task execution order, the control task execution strategy of each smart control cabinet is adjusted to obtain the optimized control task sequence of each smart control cabinet.

[0010] Based on the optimized control task sequence, control the distributed collaborative operation of each smart control cabinet in the next control cycle.

[0011] Preferably, constructing the task priority vector for each smart control cabinet in each control cycle includes: extracting the equipment load rate, operational stability index, and fault risk value from the operational status data;

[0012] Extract the task urgency, task complexity, and task dependency from the control task data; construct a task feature matrix for each smart control cabinet in each control cycle based on the equipment load rate, the operational stability index, the fault risk value, the task urgency, the task complexity, and the task dependency.

[0013] The method for obtaining the operational stability index includes: acquiring the time series of operational status data of each smart control cabinet within the current control cycle; performing a Fourier transform on the time series to extract the frequency domain features of the time series; calculating the fluctuation amplitude and periodic rate of change of the time series based on the frequency domain features; and using the weighted sum of the fluctuation amplitude and the periodic rate of change as the operational stability index.

[0014] Principal component analysis is performed on the task feature matrix to obtain the task priority vector of each smart control cabinet in each control cycle.

[0015] Preferably, generating the global task conflict graph includes:

[0016] Based on the task priority vectors of all smart control cabinets in the same control cycle, calculate the Euclidean distance between the task priority vectors of any two smart control cabinets, which is used as the task competition degree between the two smart control cabinets.

[0017] Based on the task competitiveness and the task dependency relationship in the control task data, construct a directed graph of task conflicts among all smart control cabinets;

[0018] Perform topological sorting on the directed graph of task conflicts to obtain the task conflict path of each smart control cabinet in the directed graph of task conflicts; weight and fuse the task conflict path with the task competition degree to generate a global task conflict graph.

[0019] Preferably, obtaining the task conflict probability and task execution order of each smart control cabinet within the same control cycle includes:

[0020] Based on the global task conflict graph, extract the number of conflict nodes with other smart control cabinets in the task conflict path of each smart control cabinet;

[0021] Based on the number of conflicting nodes and the degree of task competition, calculate the probability of task conflict for each smart control cabinet within the same control cycle;

[0022] Based on the task conflict paths in the global task conflict graph, the task execution order of each smart control cabinet within the same control cycle is determined.

[0023] Preferably, determining the task execution order of each smart control cabinet within the same control cycle based on the task conflict paths in the global task conflict graph includes:

[0024] A depth-first traversal is performed on each task conflict path in the global task conflict graph to generate a directed acyclic graph of task dependencies between the smart control cabinets.

[0025] Based on the directed acyclic graph of the task dependencies, the task criticality index of each smart control cabinet is calculated. The task criticality index includes in-degree, out-degree and betweenness centrality.

[0026] Construct a task execution priority matrix based on the task key indicators and the task priority vector;

[0027] Apply the critical path algorithm to the task execution priority matrix to identify the critical chain of task execution;

[0028] Based on the time constraints in the control task data of each smart control cabinet and the critical chain of task execution, a task execution time window is allocated to each smart control cabinet.

[0029] Based on the task execution time window and the probability of task conflict, an adaptive time slicing strategy is adopted to determine the final task execution order of each smart control cabinet within the same control cycle.

[0030] Preferably, adjusting the control task execution strategy of each smart control cabinet to obtain an optimized control task sequence for each smart control cabinet includes:

[0031] Based on the task conflict probability, the task adjustment weight of each smart control cabinet within the same control cycle is determined; based on the task execution order and the task adjustment weight, the control task data of each smart control cabinet is rearranged to obtain a candidate control task sequence for each smart control cabinet; the candidate control task sequence is simulated and executed to obtain the overall system operating efficiency and conflict occurrence rate in the simulation execution results.

[0032] Based on the overall system operating efficiency and the conflict occurrence rate, the candidate control task sequence is optimized to obtain the optimized control task sequence for each smart control cabinet.

[0033] Preferably, the step of reordering the control task data for each smart control cabinet includes:

[0034] For each smart control cabinet, a task description tuple is constructed from the control task data. The task description tuple includes the task identifier, original priority, execution duration, and resource requirements.

[0035] The task adjustment weights are applied to the original priorities in the task description tuple to calculate the weighted priority value.

[0036] A sequence constraint matrix is ​​constructed based on the task execution order to represent the sequential execution relationship between tasks; a priority-weighted directed acyclic graph is constructed based on the weighted priority value and the sequence constraint matrix.

[0037] A topological sorting algorithm is applied to the priority-weighted directed acyclic graph to generate an initial sorting scheme; resource conflict detection is performed on the initial sorting scheme to identify task pairs that compete for resources within overlapping time intervals.

[0038] For the identified task pairs, the weights are adjusted according to their respective tasks to resolve conflicts, and the relative execution positions are adjusted to obtain a sorting scheme after conflict resolution. The sorting scheme after conflict resolution is then mapped onto a time axis to generate a candidate control task sequence.

[0039] The candidate control task sequence is optimized for compactness to reduce idle waiting time between tasks while keeping all sequence constraints unchanged.

[0040] Preferably, the method for calculating the task competitiveness includes:

[0041] Obtain the task priority vectors of any two smart control cabinets within the same control cycle; calculate the Euclidean distance between the task priority vectors as the initial competition degree.

[0042] Based on the task dependencies in the control task data, determine whether there is a direct dependency between the two smart control cabinets; if there is a direct dependency, then positively weighted adjust the initial competitiveness; if there is no direct dependency, then negatively weighted adjust the initial competitiveness to obtain the task competitiveness.

[0043] Preferably, optimizing the candidate control task sequence to obtain an optimized control task sequence for each smart control cabinet includes:

[0044] An optimization function is constructed with the objectives of maximizing the overall operating efficiency of the system and minimizing the conflict occurrence rate; a genetic algorithm is used to iteratively optimize the candidate control task sequence to obtain the global optimal solution that satisfies the optimization function;

[0045] The candidate control task sequence corresponding to the global optimal solution is used as the optimized control task sequence for each smart control cabinet.

[0046] A distributed control system for an AI smart control cabinet, used to implement the distributed control method of the AI ​​smart control cabinet, includes: a distributed management center, which connects to the smart control cabinet through a distributed communication network to realize the real-time transmission of control commands and status data;

[0047] The distributed management center includes:

[0048] The data acquisition module is used to acquire the operating status data and control task data of each smart control cabinet in each control cycle;

[0049] The task priority analysis module is used to construct a task priority vector for each smart control cabinet in each control cycle based on the operating status data and the control task data.

[0050] The conflict graph construction module is used to generate a global task conflict graph based on the task priority vector of all smart control cabinets in the same control cycle.

[0051] The conflict analysis module is used to obtain the task conflict probability and task execution order of each smart control cabinet within the same control cycle based on the global task conflict diagram.

[0052] The task scheduling module is used to adjust the control task execution strategy of each smart control cabinet based on the task conflict probability and the task execution order, so as to obtain the optimized control task sequence of each smart control cabinet.

[0053] The collaborative control module is used to control the distributed collaborative operation of each smart control cabinet in the next control cycle according to the optimized control task sequence.

[0054] The modules are connected to each other via wired and / or wireless means.

[0055] The technical effects and advantages of the distributed control system and method for AI smart control cabinet of this invention are as follows:

[0056] This invention improves the overall operational efficiency of intelligent power systems by effectively avoiding resource contention problems common in traditional control systems through conflict prediction and coordination mechanisms. It achieves precise dynamic adjustment of task priorities, significantly reducing the system's task conflict rate and maintaining good responsiveness even under high load conditions. System resource utilization is improved, resulting in significant energy savings and enhanced rapid response to emergencies. Furthermore, this invention possesses fault prediction and risk prevention capabilities, eliminating potential faults at their inception through intelligent analysis and early warning, thus improving the safety and reliability of the power system. Additionally, the adaptive learning characteristics of this invention enable the system to continuously optimize its operating strategies, adapting to complex and changing operating environments and achieving long-term stable and efficient operation. In practical applications, it significantly reduces the need for manual intervention, lowers maintenance costs, and extends equipment lifespan. Attached Figure Description

[0057] Figure 1 This is a schematic diagram of a distributed control method for an AI smart control cabinet according to the present invention;

[0058] Figure 2 This is a schematic diagram of a distributed control system for an AI smart control cabinet according to the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] This invention proposes a distributed control system and method for an AI-powered intelligent control cabinet. Please refer to [link / reference]. Figure 1 The diagram illustrates a distributed control method for an AI smart control cabinet according to an embodiment of the present invention. The method includes:

[0061] Step S1: Obtain the operating status data and control task data of each smart control cabinet in each control cycle.

[0062] Multiple smart control cabinets are deployed in a distributed system, each responsible for managing the power equipment, industrial equipment, or other intelligent control objects in its assigned area. The smart control cabinets collect real-time operational status data of themselves and the equipment they manage through a built-in sensor network, including but not limited to equipment load rate, operational stability indicators, and fault risk values; simultaneously, they receive control task data from the system dispatch center or upper-level control units, including but not limited to task urgency, task complexity, and task dependencies.

[0063] It should be noted that each smart control cabinet is equipped with an edge computing unit, which can perform preliminary processing and analysis on the collected data and transmit the data to the central control system or other smart control cabinets via a distributed network. The smart control cabinets can communicate directly with each other, forming a distributed collaborative network.

[0064] In one implementation of this invention, the control cycle is set to once every 5 seconds.

[0065] In one implementation of this invention, the runtime status data is standardized by using the Z-score standardization method to map all indicators to the same scale for subsequent analysis. The urgency of tasks in the control task data is represented by a value from 1 to 10, with higher values ​​indicating more urgent tasks; task complexity is represented by a value from 1 to 5, with higher values ​​indicating more complex tasks; task dependencies are represented using a directed graph, where dependent tasks must be executed before the tasks they depend on.

[0066] The following steps all use processed operational status data and control task data for analysis.

[0067] Step S2: Based on the operating status data and the control task data, construct a task priority vector for each smart control cabinet in each control cycle.

[0068] The task priority vector is a quantitative representation reflecting the relative importance of various control tasks in a smart control cabinet. By extracting and fusing features from operational status data and control task data, multi-dimensional task characteristics are compressed into a single vector representation, facilitating subsequent task coordination and conflict detection in a distributed environment. The dimensions of the task priority vector depend on the type and number of features of the control task, typically including multiple dimensions such as task urgency, impact on system stability, resource consumption, and dependency strength.

[0069] Preferably, in some possible implementations of the embodiments of the present invention, constructing a task priority vector for each smart control cabinet in each control cycle includes: extracting equipment load rate, operational stability index, and fault risk value from the operational status data; extracting task urgency, task complexity, and task dependency from the control task data; and constructing a task feature matrix for each smart control cabinet in each control cycle based on the equipment load rate, operational stability index, fault risk value, task urgency, task complexity, and task dependency.

[0070] Equipment load rate reflects the current load status of the equipment managed by the intelligent control cabinet, usually expressed as a percentage. When the equipment load rate is too high, adding new control tasks may cause equipment overload, affecting system stability. Operational stability indicators represent the stability of the system under its current operating state; higher stability means a stronger ability to resist external interference. Fault risk value predicts the probability of system failure under its current state; a higher risk value indicates lower system security, requiring priority handling of related tasks.

[0071] The method for obtaining the operational stability index includes: obtaining the time series of operational status data of each smart control cabinet in the current control cycle; performing Fourier transform on the time series to extract the frequency domain features of the time series; calculating the fluctuation amplitude and periodic rate of change of the time series based on the frequency domain features; and using the weighted sum of the fluctuation amplitude and periodic rate of change as the operational stability index.

[0072] The time series of operational status data reflects the changes in the operational status of the intelligent control cabinet within the control cycle. By performing a Fourier transform on the time series, the time-domain signal can be converted into a frequency-domain signal, extracting the implicit periodic features. Frequency-domain features include power spectral density, dominant frequency components, and harmonic ratios, which reflect the stability and fluctuations of the system operation. Fluctuation amplitude represents the magnitude of changes in the system's operational status; the greater the fluctuation, the worse the system stability. The periodic rate of change represents the regularity of the changes in the system's operational status; the higher the rate of change, the more regular the system operation and the better the stability.

[0073] In one implementation of this invention, the weighting of fluctuation amplitude and periodic rate of change is as follows: Operational stability index = 0.6 × (1 - normalized fluctuation amplitude) + 0.4 × normalized periodic rate of change. Here, the normalization operation maps the value to the interval [0,1]. Smaller fluctuation amplitude results in higher stability; larger periodic rate of change also results in higher stability.

[0074] Task urgency reflects the time sensitivity of the control task; the higher the urgency, the faster the task needs to be executed. Task complexity represents the complexity and resource requirements of the control task; the higher the complexity, the more difficult the task is to execute. Task dependencies describe the sequential execution constraints between control tasks; the more complex the dependencies, the more difficult the task coordination.

[0075] In this embodiment of the invention, a task feature matrix is ​​constructed by combining equipment load rate, operational stability index, fault risk value, task urgency, task complexity, and task dependencies. Each row of the task feature matrix corresponds to a control task, and each column corresponds to a feature dimension. Since task dependencies are usually represented in a graph structure, they need to be converted into numerical features. The number of preceding and subsequent dependent tasks for each task can be calculated as a numerical representation of the task dependencies.

[0076] Principal Component Analysis (PCA) of the task feature matrix can reduce feature dimensionality, extract the most representative feature combinations, and form a task priority vector. PCA can preserve the main variation information of the data while reducing redundancy and noise, making subsequent task priority calculations more efficient and accurate.

[0077] In one implementation of this invention, the top few principal components that explain a cumulative 85% of the variance in the principal component analysis results are retained to form a task priority vector.

[0078] Step S3: Generate a global task conflict diagram for the distributed system based on the task priority vectors of all smart control cabinets within the same control cycle.

[0079] A global task conflict graph is a directed graph structure used to represent potential task execution conflicts between intelligent control cabinets in a distributed system. In a distributed system, the control tasks of different intelligent control cabinets may affect each other, such as competing for shared resources or having sequential execution dependencies. These potential conflicts can impact the overall stability and efficiency of the system. By constructing a global task conflict graph, the task conflict situation in the system can be visually represented and analyzed, providing a basis for subsequent task scheduling and optimization.

[0080] Preferably, in some possible implementations of the embodiments of the present invention, generating a global task conflict graph of the distributed system includes: calculating the Euclidean distance between the task priority vectors of any two smart control cabinets based on the task priority vectors of all smart control cabinets in the same control cycle, as the task competition degree of the corresponding two smart control cabinets; constructing a directed task conflict graph among all smart control cabinets in the distributed system based on the task competition degree and the task dependency relationship in the control task data; performing topological sorting on the directed task conflict graph to obtain the task conflict path of each smart control cabinet in the directed task conflict graph; and weightedly fusing the task conflict path and the task competition degree to generate a global task conflict graph of the distributed system.

[0081] The task priority vector reflects the importance and urgency of the current control task of the intelligent control cabinet. When the task priority vectors of two control cabinets are similar, it means that they may need to perform tasks of similar importance at the same time, thus increasing the possibility of task competition and conflict. Euclidean distance is a commonly used method to measure the similarity between two vectors; the smaller the distance, the higher the similarity, and the greater the corresponding task competition.

[0082] In this embodiment of the invention, the Euclidean distance d(A,B) between the task priority vectors V_A and V_B of any two smart control cabinets A and B is calculated using the following formula:

[0083] Where V_A_i and V_B_i are the i-th components of vectors V_A and V_B, respectively.

[0084] Since a larger Euclidean distance indicates a greater difference between two vectors, and task competitiveness is directly proportional to vector similarity, it is necessary to transform the Euclidean distance. In this embodiment of the invention, the task competitiveness C(A,B) is calculated as follows:

[0085] Through this transformation, the smaller the Euclidean distance d(A,B), the closer the task competitiveness C(A,B) is to 1; the larger the Euclidean distance d(A,B), the closer the task competitiveness C(A,B) is to 0.

[0086] When constructing a directed graph of task conflicts, in addition to considering task competition, it is also necessary to consider the task dependencies in the control task data. Task dependencies reflect the sequential execution constraints between tasks in different control cabinets. When task A depends on task B, task B must be completed before task A. This dependency also increases the possibility of task conflicts.

[0087] In this embodiment of the invention, the task conflict directed graph is a weighted directed graph, where nodes represent smart control cabinets and edges represent task conflict relationships between control cabinets. The weight of an edge is determined by both the task contention degree and the task dependency strength. When there is a task dependency relationship between two control cabinets, a directed edge is added between the corresponding nodes, with the edge pointing from the dependent task to the dependent task; when the task contention degree between two control cabinets exceeds a preset threshold, an undirected edge (or a bidirectional edge) is also added between the corresponding nodes.

[0088] In one implementation of this invention, the preset threshold for task contention is set to 0.6.

[0089] Topological sorting of the task conflict directed graph yields a sequence of nodes that satisfies all dependency constraints. While the topological sorting reflects the ideal execution order of tasks within the smart control cabinet, it may not completely eliminate conflicts caused by task contention. Therefore, further analysis of the position and connectivity of each smart control cabinet within the task conflict directed graph is needed to obtain its task conflict paths.

[0090] Task conflict paths refer to all possible paths from a source node to a target node in a directed graph of task conflicts, reflecting the propagation and scope of impact of task conflicts. For each intelligent control cabinet, all conflict paths that it serves as both a source and a target node need to be considered. The more numerous and longer the conflict paths, the more severe the conflict between the tasks of that control cabinet and those of other control cabinets in the system, requiring more careful scheduling and optimization.

[0091] By weighting and fusing task conflict paths with task competitiveness, a more comprehensive conflict assessment can be obtained. In this embodiment of the invention, the global task conflict graph is based on a directed task conflict graph, with the weight of each edge adjusted. The weight adjustment formula is as follows:

[0092] W_new(A,B)=h×W_old(A,B)+(1-h)×P(A,B);

[0093] Where W_new(A,B) is the adjusted weight, W_old(A,B) is the original edge weight (task competitiveness), P(A,B) is the evaluation value of all conflict paths from node A to node B, and h is the weight coefficient, with a value range of [0,1].

[0094] In one implementation of this invention, h is set to 0.7. P(A,B) is calculated as the normalized value of the weighted sum of the number of paths and the path length.

[0095] Step S4: Based on the global task conflict diagram, obtain the task conflict probability and task execution order of each smart control cabinet within the same control cycle.

[0096] By analyzing the topology and conflict intensity of the global task conflict graph, the probability of conflict between tasks in each smart control cabinet and tasks in other control cabinets is calculated, and a task execution order that minimizes conflict is determined. The task conflict probability reflects the likelihood of a task encountering resource contention or dependency conflicts during execution, while the task execution order is the optimal execution path based on the conflict graph and overall system operating efficiency.

[0097] Preferably, in some possible implementations of the embodiments of the present invention, obtaining the task conflict probability and task execution order of each smart control cabinet within the same control cycle includes: extracting the number of conflict nodes between each smart control cabinet and other smart control cabinets in the task conflict path of each smart control cabinet according to the global task conflict graph; calculating the task conflict probability of each smart control cabinet within the same control cycle according to the number of conflict nodes and the task competition degree; and determining the task execution order of each smart control cabinet within the same control cycle according to the task conflict path in the global task conflict graph.

[0098] A conflict node refers to another smart control cabinet in the global task conflict graph that has a direct connection (i.e., a conflicting relationship) with the target smart control cabinet. The more conflict nodes there are, the more conflicts the smart control cabinet's task has with the tasks of other control cabinets in the system, the greater the difficulty of task coordination, and the higher the probability of task conflict.

[0099] In this embodiment of the invention, conflicting nodes include not only nodes directly connected to the target control cabinet, but also nodes indirectly connected through task conflict paths. By analyzing task conflict paths, control cabinets that appear unrelated but may actually cause conflict through a chain reaction can be identified. This analysis method takes into account the complex topology of the system and can more comprehensively assess potential task conflicts.

[0100] The task conflict probability of each smart control cabinet is calculated based on the number of conflicting nodes and the task competitiveness. The number of conflicting nodes reflects the scope of the conflict, while the task competitiveness reflects the intensity of the conflict. Combining the two allows for a more accurate assessment of the likelihood of task conflict. In this embodiment of the invention, the formula for calculating the task conflict probability P is:

[0101] P=1-exp(-(z×N+(1-z)×C_avg));

[0102] Where N is the normalized number of conflicting nodes, C_avg is the average task contention degree of all edges connected to the control cabinet, z is the weight coefficient with a value range of [0,1], and exp represents the natural exponential function.

[0103] In one implementation of this invention, z is set to 0.65. This calculation method ensures that as the number of conflicting nodes or the average task contention increases, the probability of task conflict also increases, but the rate of increase gradually slows down and approaches but does not exceed 1, which is within the defined range of probability.

[0104] Based on the task conflict paths in the global task conflict graph, the task execution order of each intelligent control cabinet within the same control cycle is determined. An ideal task execution order should satisfy all dependency constraints and minimize conflicts. In this embodiment of the invention, a method based on critical path analysis is used to determine the task execution order: First, the global task conflict graph is converted into a task-dependent directed acyclic graph (DAG); then, the earliest start time and latest end time of each node in the DAG are calculated; finally, the final task execution order is determined based on the node's time constraints and conflict probability.

[0105] Preferably, in some possible implementations of the embodiments of the present invention, determining the task execution order of each smart control cabinet within the same control cycle based on the task conflict paths in the global task conflict graph includes: performing a depth-first traversal on each task conflict path in the global task conflict graph to generate a directed acyclic graph of task dependencies among the smart control cabinets; calculating the task criticality index of each smart control cabinet based on the directed acyclic graph of task dependencies, the task criticality index including in-degree, out-degree, and betweenness centrality; constructing a task execution priority matrix based on the task criticality index and the task priority vector; applying a critical path algorithm to the task execution priority matrix to identify the task execution critical chain in the distributed system; allocating a task execution time window for each smart control cabinet based on the task execution critical chain and the time constraints in the control task data of each smart control cabinet; and determining the final task execution order of each smart control cabinet within the same control cycle based on the task execution time window and the task conflict probability using an adaptive time slicing strategy.

[0106] Depth-first search (DFS) is a graph search algorithm that starts from a vertex in a graph, traverses a path to the end, backtracks to the previous node, and continues along another path to the end, until all vertices have been visited. By performing a DFS on every conflict path in the global task conflict graph, all potential conflict links can be identified, and this information can be integrated into a directed acyclic graph (DAG) of task dependencies.

[0107] In this embodiment of the invention, the depth-first traversal is implemented recursively. First, all edges in the global task conflict graph are sorted in descending order of weight (conflict intensity). Then, the traversal starts from the edge with the largest weight, ensuring that the path with the most severe conflict is processed first. During the traversal, if a cycle (circular dependency) is found, it needs to be broken to ensure that the generated graph is a directed acyclic graph. The principle for breaking the cycle is to remove the edge with the smallest weight.

[0108] Based on a directed acyclic graph (DAG) of task dependencies, the task criticality index for each smart control cabinet is calculated. The task criticality index reflects the importance and influence of the smart control cabinet in the distributed system task network, and includes three indicators: in-degree, out-degree, and betweenness centrality. The in-degree represents the number of other control cabinets that depend on it, reflecting the preceding influence of its task; the out-degree represents the number of other control cabinets that it depends on, reflecting the subsequent dependency of its task; and the betweenness centrality represents the degree to which the control cabinet acts as a "bridge" in the entire network. The higher the betweenness centrality, the more critical its role in task coordination.

[0109] In this embodiment of the invention, the formula for calculating the betweenness centrality BC(v) is:

[0110] Here, sig(s,t) represents the number of shortest paths from node s to node t, and sig(s,t|v) represents the number of shortest paths from node s to node t that must pass through node v.

[0111] Based on the task criticality indicators and task priority vectors, a task execution priority matrix is ​​constructed. This matrix is ​​a multi-dimensional matrix that comprehensively considers both the task's own priority and the influence of the system network, and is used to guide the determination of the task execution order.

[0112] Applying the critical path algorithm to the task execution priority matrix identifies the critical chain of task execution in a distributed system. The critical path is the longest path from the start node to the end node, and the tasks on this path determine the shortest completion time for the entire project. In a distributed system, the critical chain of task execution refers to the sequence of critical tasks that significantly impacts the overall system efficiency; delays in tasks on the critical chain directly lead to delays in the entire system.

[0113] In this embodiment of the invention, the critical path algorithm is implemented based on a task execution priority matrix and a directed acyclic graph of task dependencies. First, the earliest start time (ES) and earliest end time (EF) of each node are calculated; then, the latest start time (LS) and latest end time (LF) of each node are calculated; finally, the time slack (Slack = LS - ES) of each node is calculated, and nodes with a time slack of 0 constitute the critical path.

[0114] Based on the time constraints in the control task data of each smart control cabinet and the critical chain of task execution, a task execution time window is assigned to each smart control cabinet. A time window refers to the range of time within which a task is allowed to begin execution, including the earliest start time and the latest start time. For tasks on the critical chain, the time window is more stringent, typically requiring execution near the earliest start time; for non-critical chain tasks, the time window is more lenient, allowing for flexible scheduling within the permissible range.

[0115] In this embodiment of the invention, the time window allocation strategy is based on the following principles: First, ensure that tasks on the critical chain can be executed as planned; second, make reasonable use of the time slack of non-critical chain tasks to reduce resource conflicts; and finally, consider the dependencies between tasks to ensure that the order of task execution is correct.

[0116] Based on the task execution time window and task conflict probability, an adaptive time slicing strategy is adopted to determine the final task execution order of each smart control cabinet within the same control cycle. The adaptive time slicing strategy is a method for dynamically adjusting task execution time, automatically adjusting the size and allocation of task execution time slices according to task conflict probability and system load.

[0117] In this embodiment of the invention, the adaptive time slicing strategy is implemented as follows: First, the control cycle is divided into multiple time slices; then, based on the task conflict probability, a larger time slice or exclusive time slice is allocated to tasks with a high conflict probability, and a shared time slice is allocated to tasks with a low conflict probability; finally, based on the constraints of the task execution time window, the specific execution time point and order of each task are determined.

[0118] In one implementation of this invention, the time slice size is set to 1 / 20 of the control period, i.e., 0.25 seconds (assuming the control period is 5 seconds). When the task conflict probability is greater than 0.8, an exclusive time slice is allocated; when the task conflict probability is between 0.5 and 0.8, a 50% overlapping time slice is allocated; when the task conflict probability is less than 0.5, a fully shared time slice is allocated.

[0119] Step S5: Based on the task conflict probability and the task execution order, adjust the control task execution strategy of each smart control cabinet to obtain the optimized control task sequence of each smart control cabinet.

[0120] Based on the probability of task conflicts and the order of task execution, the original control task execution strategy of the intelligent control cabinet is adjusted, including task priority rearrangement, execution time window allocation, and resource reservation, thereby obtaining an optimized control task sequence. This optimized control task sequence considers not only the importance and urgency of the tasks themselves but also the overall system coordination, ensuring correct task execution while minimizing task conflicts within the system.

[0121] Preferably, in some possible implementations of the embodiments of the present invention, adjusting the control task execution strategy of each smart control cabinet to obtain an optimized control task sequence for each smart control cabinet includes: determining the task adjustment weight of each smart control cabinet within the same control cycle based on the task conflict probability; and rearranging the control task data of each smart control cabinet according to the task execution order and the task adjustment weight to obtain a candidate control task sequence for each smart control cabinet.

[0122] Task adjustment weight is an indicator that measures the extent of task adjustments in the intelligent control cabinet. The higher the probability of task conflict, the greater the necessity for task adjustment, and the greater the corresponding task adjustment weight. In this embodiment of the invention, the formula for calculating the task adjustment weight W is:

[0123] W = k × P n Where P is the task conflict probability, and k and n are adjustment parameters used to control the growth rate and range of the weights.

[0124] In one implementation of this invention, k is set to 2 and n to 0.5. This setting allows the task adjustment weight to increase slowly when the conflict probability is low, and to increase rapidly when the conflict probability is high, thereby enabling more significant adjustments to tasks with high conflict risk.

[0125] Candidate control task sequences are simulated for execution, and the overall system efficiency and conflict rate are obtained from the simulation results. Simulation is an important means of evaluating the effectiveness of task sequences before actual deployment. By constructing a digital twin model of the distributed system, the execution process of the task sequences is simulated in a virtual environment to obtain key performance indicators and provide data support for subsequent optimization.

[0126] In this embodiment of the invention, the simulation execution employs a discrete event simulation method, discretizing the time within the control cycle into multiple event points, each event point corresponding to the start or end of one or more tasks. During the simulation, system state changes are tracked in real time, including resource usage, task execution progress, and control command transmission delays, thereby evaluating the execution effect of candidate control task sequences.

[0127] Overall system operating efficiency is a comprehensive indicator for measuring the task execution performance of a distributed system, reflecting the system's ability to complete effective work per unit of time. In this embodiment of the invention, the formula for calculating the overall system operating efficiency η is:

[0128] Where W_i is the importance weight of the i-th task, C_i is the completion degree of the i-th task, T is the total execution time, and R is the total system resources. This formula considers three aspects: task completion, time utilization, and resource utilization, and can comprehensively reflect the system's operating efficiency.

[0129] The conflict occurrence rate (CR) is the ratio of the actual number of task conflicts to the theoretically possible number of conflicts during simulated execution. It is an important indicator for evaluating the coordination of task sequences. In this embodiment of the invention, the formula for calculating the conflict occurrence rate CR is:

[0130] Here, Nc represents the actual number of conflicts that occurred, and Np represents the theoretically possible number of conflicts. The conflict count is based on three types of conflicts: resource contention, timing violations, and data consistency.

[0131] Preferably, random disturbances are introduced during the simulation process to simulate communication delays, computational biases, and external interference that may occur in the real environment, thereby enhancing the reliability and robustness of the simulation results. The magnitude of the random disturbances is determined based on the fluctuation statistics in historical operating data to ensure the similarity between the simulated environment and the actual environment.

[0132] In one implementation of this invention, the simulation execution adopts the Monte Carlo method, which performs 100 repeated simulations for each candidate control task sequence, introducing different random disturbances in each simulation, and finally taking the average value as the evaluation result of the overall system operating efficiency and conflict occurrence rate.

[0133] Based on the overall system operating efficiency and conflict incidence rate, the candidate control task sequence is optimized to obtain the optimized control task sequence for each smart control cabinet. The optimization process aims to find a balance point that ensures efficient system operation while minimizing task conflicts.

[0134] Preferably, in some possible implementations of the embodiments of the present invention, optimizing the candidate control task sequence to obtain the optimized control task sequence for each smart control cabinet includes: constructing an optimization function with the goal of maximizing the overall system operating efficiency and minimizing the conflict occurrence rate; using a genetic algorithm to iteratively optimize the candidate control task sequence to obtain the global optimal solution that satisfies the optimization function; and using the candidate control task sequence corresponding to the global optimal solution as the optimized control task sequence for each smart control cabinet.

[0135] An optimization function is a mathematical expression that evaluates the merits of candidate control task sequences and guides the optimization algorithm in searching for the optimal solution. In this invention, the optimization objectives include two aspects: maximizing the overall system efficiency and minimizing the conflict rate. These two objectives may conflict; for example, improving efficiency may increase the risk of conflict, while reducing conflict may decrease efficiency. Therefore, a balance needs to be found between the two.

[0136] In this embodiment of the invention, the optimization function F is defined as follows:

[0137] F = a × E - (1 - a) × C;

[0138] Where E is the overall system operating efficiency (range [0,1]), C is the conflict occurrence rate (range [0,1]), and a is the weighting coefficient (range [0,1]), used to balance the relative importance of the two objectives.

[0139] In one implementation of this invention, the value of 'a' is 0.7, indicating that the system prioritizes improving operational efficiency while also considering reducing conflicts. When the value of 'a' is 1, the system focuses solely on operational efficiency; when the value of 'a' is 0, the system focuses solely on reducing conflicts. By adjusting the value of 'a', the emphasis of the optimization objective can be flexibly adjusted according to actual needs.

[0140] Genetic algorithms are optimization algorithms based on natural selection and genetic mechanisms, suitable for complex combinatorial optimization problems. In this embodiment of the invention, a genetic algorithm is used to iteratively optimize candidate control task sequences, searching for the globally optimal solution that satisfies the optimization function. The basic principle of the genetic algorithm is: by simulating evolutionary operations such as natural selection, crossover, and mutation, starting from an initial set of solutions (population), new solutions are gradually generated, and the quality of the solutions is evaluated according to the fitness function (i.e., the optimization function). Solutions with high fitness are retained, while solutions with low fitness are eliminated. After multiple generations of evolution, the optimal solution in the population gradually approaches the globally optimal solution.

[0141] In this embodiment of the invention, the specific implementation of the genetic algorithm includes the following steps:

[0142] 1) Initialize the population: Generate a set of random candidate control task sequences as the initial population;

[0143] 2) Evaluate fitness: Calculate the optimization function value of each candidate solution as its fitness;

[0144] 3) Selection operation: Based on the fitness level, parent individuals are selected using methods such as roulette or tournaments;

[0145] 4) Crossover operation: Pair the selected parent individuals together, exchange parts of their task sequences, and generate offspring individuals;

[0146] 5) Mutation operation: Randomly mutate the task sequence of offspring individuals with a certain probability to increase the diversity of the population;

[0147] 6) Population renewal: Based on fitness, select superior individuals from the parent and offspring generations to form a new generation of the population;

[0148] 7) Termination condition: The algorithm terminates when the maximum number of iterations is reached or the fitness no longer improves significantly;

[0149] 8) Output: Return the individual with the highest fitness in the final population as the global optimal solution.

[0150] In one implementation of this invention, the population size is set to 100, the maximum number of iterations is set to 200, the crossover probability is set to 0.8, and the mutation probability is set to 0.1.

[0151] In implementing genetic algorithms, special attention needs to be paid to the encoding and decoding methods of task sequences, as well as how to handle task dependency constraints. In this embodiment of the invention, a task priority list encoding is used, that is, tasks are sorted according to priority, and during decoding, tasks are executed in priority order, while considering dependency constraints. For candidate solutions that violate dependency constraints, repair operations can be used to make them satisfy the constraints, or a larger penalty term can be applied to reduce their fitness.

[0152] The candidate control task sequence corresponding to the global optimal solution is used as the optimized control task sequence for each smart control cabinet. The global optimal solution is the best task scheduling scheme found under the current conditions after iterative optimization by a genetic algorithm, achieving the best balance between overall system efficiency and conflict rate. The optimized control task sequence contains information such as the tasks that each smart control cabinet should execute in the next control cycle, the execution order of the tasks, the start time, and the completion time, providing specific execution guidance for the distributed collaborative operation of the smart control cabinets.

[0153] Preferably, in some possible implementations of the embodiments of the present invention, the control task data of each smart control cabinet is rearranged, including: constructing a task description tuple for the control task data of each smart control cabinet, wherein the task description tuple contains a task identifier, original priority, execution duration and resource requirements; applying the task adjustment weight to the original priority in the task description tuple to calculate a weighted priority value.

[0154] A sequence constraint matrix is ​​constructed based on the task execution order to represent the sequential execution relationship between tasks. A priority-weighted directed acyclic graph (DAG) is constructed based on the weighted priority values ​​and the sequence constraint matrix. A topological sorting algorithm is applied to the priority-weighted DAG to generate an initial sorting scheme that satisfies dependency constraints. Resource conflict detection is performed on the initial sorting scheme to identify task pairs with resource contention within overlapping time intervals. For the identified task pairs, conflict resolution is achieved by adjusting the weights of each task and adjusting their relative execution positions to obtain a conflict-resolved sorting scheme. The conflict-resolved sorting scheme is then mapped onto a timeline to generate a candidate control task sequence containing precise execution time windows. The candidate control task sequence is then optimized for compactness to reduce idle waiting time between tasks while maintaining all sequence constraints unchanged.

[0155] A task description tuple is a structured representation of control task data, containing key attribute information about the task. The task identifier uniquely identifies a task, the initial priority indicates the task's initial importance, the execution duration indicates the time required to complete the task, and the resource requirement indicates the system resources consumed during task execution. By constructing task description tuples, complex control task data can be transformed into a unified structured format, facilitating subsequent processing and analysis.

[0156] In this embodiment of the invention, the task description tuple is in the form of: Task = (ID, Pr, Dur, Res), where ID is the task identifier, Pr is the original priority (range 1-10), Dur is the execution duration (in seconds), and Res is a vector of resource requirements, representing the task's requirements for various resources.

[0157] The task adjustment weights are applied to the original priorities in the task description tuples to calculate the weighted priority value. The weighted priority value is a modified value based on the original priorities, taking into account the task adjustment weights, reflecting the actual importance of the task in the current system state. In this embodiment of the invention, the formula for calculating the weighted priority value WP is:

[0158] WP = Pr × (1 + W × f(P));

[0159] Where Pr is the original priority, W is the task adjustment weight, P is the task conflict probability, and f(P) is the conflict probability adjustment function, which is used to control the influence of conflict probability on priority.

[0160] In one implementation of this invention, f(P) = P 2 This setting causes the impact of conflict probability on priority to grow in a quadratic function manner, with a smaller impact when the conflict probability is low and a significantly larger impact when the conflict probability is high.

[0161] A sequence constraint matrix is ​​constructed based on the task execution order to represent the sequential execution relationships between tasks. The sequence constraint matrix is ​​a two-dimensional matrix, where each element represents a sequential constraint relationship between tasks. In this embodiment of the invention, the sequence constraint matrix S is defined as follows:

[0162] S[i,j] = 1, if task i must be executed before task j;

[0163] S[i,j] = 0 if there is no direct constraint relationship between task i and task j;

[0164] S[i,j] = -1, if task j must be executed before task i;

[0165] Based on weighted priority values ​​and a sequence constraint matrix, a priority-weighted directed acyclic graph (DAG) is constructed. A priority-weighted DAG is a special type of directed graph where nodes represent tasks, edges represent dependencies between tasks, and the weight of a node is the weighted priority value of the task. This graph structure preserves the dependency constraints between tasks while also considering the actual importance of tasks, providing a foundation for subsequent topological sorting.

[0166] A topological sorting algorithm is applied to a priority-weighted directed acyclic graph (DAG) to generate an initial sorting scheme that satisfies dependency constraints. Topological sorting is an algorithm that arranges all nodes in a DAG into a linear sequence such that for each edge (u, v), node u appears before node v in the sequence. In this embodiment of the invention, a topological sorting algorithm based on depth-first search (DFS) is used, with the specific steps as follows:

[0167] 1) Perform a depth-first search on all nodes in the graph;

[0168] 2) During the search process, when all of a node's neighboring nodes have been visited, add that node to the result sequence;

[0169] 3) The final sequence, after being reversed, is the result of topological sorting.

[0170] The initial sorting scheme satisfies all dependency constraints, but resource conflicts may exist. Therefore, resource conflict detection is needed for the initial sorting scheme to identify task pairs that compete for resources within overlapping time intervals. The basic principle of resource conflict detection is: if the execution times of two tasks overlap and they require the same resources, then these two tasks have a resource conflict.

[0171] In this embodiment of the invention, the specific steps for resource conflict detection include: first, calculating the expected start and end times of each task based on the initial sorting scheme and task execution duration; then, for each pair of tasks that may be executed simultaneously, checking whether their resource requirements overlap; and finally, marking task pairs with overlapping resource requirements and execution times as conflicting task pairs.

[0172] For each identified task pair, conflict resolution is achieved by adjusting the weights of each task and adjusting their relative execution positions to obtain a sorting scheme after conflict resolution. The goal of conflict resolution is to eliminate resource conflicts by adjusting the execution order or execution time of tasks, while maintaining the original task priorities and dependencies as much as possible.

[0173] In this embodiment of the invention, the conflict resolution strategy is based on task adjustment weights: for a pair of conflicting tasks, the task with the smaller adjustment weight is given priority to yield, i.e., its execution time is postponed; if the adjustment weights of the two tasks are similar, their weighted priority values ​​are considered, and the task with the lower priority yields; if the conflict still cannot be resolved, the overall impact is considered, and an adjustment scheme with less impact on the system is selected.

[0174] The conflict-resolved sorting scheme is time-mapped to generate a sequence of candidate control tasks containing precise execution time windows. Time-mapping is the process of converting the relative execution order of tasks into specific time points, including calculating the specific start and end times of each task. In this embodiment of the invention, the time-mapping adopts a forward scheduling method, starting from the beginning of the control cycle and arranging the execution time of each task sequentially according to task dependencies and resource constraints.

[0175] In one implementation of this invention, the specific steps of timeline mapping include: first, setting the task with an in-degree of 0 (no prerequisites) as the earliest possible start time; then, calculating the start time of other tasks one by one according to the topological sorting order, wherein the start time of a task is equal to the maximum value of the end times of all its prerequisite tasks; finally, the end time of a task is equal to the start time plus the execution duration.

[0176] The candidate control task sequence is optimized for compactness to reduce idle waiting time between tasks while keeping all sequence constraints unchanged. The goal of compactness optimization is to improve system resource utilization and reduce idle time during task execution, thereby improving the overall system execution efficiency. In this embodiment of the invention, compactness optimization adopts a forward-moving strategy, that is, moving tasks forward as much as possible without violating dependency constraints and resource constraints, thus reducing gaps between tasks.

[0177] In one implementation of this invention, the specific steps for compactness optimization include: first, calculating the earliest possible start time and the latest required start time for each task; then, within this time window, attempting to move the task forward until it can no longer be moved; finally, checking resource constraints to ensure that moving the task does not lead to new resource conflicts. In this way, idle waiting time between tasks can be minimized, improving system compactness and execution efficiency.

[0178] Preferably, in some possible implementations of the embodiments of the present invention, the method for calculating the task competitiveness includes: obtaining the task priority vectors of any two smart control cabinets within the same control cycle; calculating the Euclidean distance between the task priority vectors as the initial competitiveness; determining whether there is a direct dependency relationship between the two smart control cabinets based on the task dependency relationship in the control task data; if there is a direct dependency relationship, then positively weighting the initial competitiveness; if there is no direct dependency relationship, then negatively weighting the initial competitiveness to obtain the task competitiveness.

[0179] The task priority vector is a quantitative representation of the current control task priority of the intelligent control cabinet. The dimension and specific meaning of the vector are determined by the results of principal component analysis. By comparing the task priority vectors of different control cabinets, the task similarity and competition between them can be assessed.

[0180] In this embodiment of the invention, task priority vectors V_A and V_B are obtained for any two smart control cabinets A and B within the same control cycle, with a dimension of n. The initial competition level can be obtained by calculating the Euclidean distance d(V_A,V_B) between these two vectors.

[0181] Euclidean distance is the straight-line distance between two points in n-dimensional space. The smaller the Euclidean distance, the more similar the two vectors are, and the greater the initial competition. The larger the Euclidean distance, the less similar the two vectors are, and the smaller the initial competition.

[0182] In this embodiment of the invention, the formula for converting Euclidean distance into initial competition degree is:

[0183]

[0184] Thus, when the Euclidean distance is 0, the initial competition degree is 1 (maximum value); when the Euclidean distance approaches infinity, the initial competition degree approaches 0 (minimum value).

[0185] Based on the task dependencies in the control task data, determine whether a direct dependency exists between the two intelligent control cabinets. A direct dependency means that the task execution of one control cabinet depends on the task completion of the other control cabinet. When a direct dependency exists between two control cabinets, their task execution needs to be coordinated; otherwise, it may lead to system performance degradation or task failure.

[0186] In this embodiment of the invention, by analyzing the dependency graph in the control task data, it is determined whether there is a direct connection between two smart control cabinets. If there is, it is considered that there is a direct dependency between them.

[0187] If a direct dependency exists, the initial competitiveness level is positively weighted and adjusted; if no direct dependency exists, the initial competitiveness level is negatively weighted and adjusted to obtain the final task competitiveness level. A positive weighted adjustment increases the initial competitiveness level, reflecting that dependencies increase the necessity for task coordination and potential conflicts; a negative weighted adjustment decreases the initial competitiveness level, reflecting that tasks without dependencies have a lower probability of conflict.

[0188] In this embodiment of the invention, the formula for weighted adjustment is:

[0189] If a direct dependency exists: C = In_C × (1 + d);

[0190] If there is no direct dependency: C = In_C × (1-d);

[0191] Where d is the adjustment coefficient, and its value ranges from [0,1].

[0192] In one implementation of this invention, d is set to 0.3. This means that when a direct dependency exists, the task contention level increases by 30% compared to the initial contention level; when no direct dependency exists, the task contention level decreases by 30% compared to the initial contention level.

[0193] Step S6: Based on the optimized control task sequence, control the distributed collaborative operation of each smart control cabinet in the next control cycle to avoid control conflicts and execution sequence errors.

[0194] The optimized control task sequence is distributed to each intelligent control cabinet, guiding their operation in the next control cycle. Through the distributed system's communication network, each intelligent control cabinet can perceive the execution status of other control cabinets in real time and coordinate its own task execution according to the optimized control task sequence, thereby achieving distributed collaborative operation of the entire system. Simultaneously, each intelligent control cabinet continuously collects new operational status data, providing foundational data for optimization in the next control cycle.

[0195] Preferably, in some possible implementations of the embodiments of the present invention, controlling the distributed collaborative operation of each smart control cabinet in the next control cycle includes: generating a control instruction sequence for each smart control cabinet in the next control cycle according to the optimized control task sequence; sending the control instruction sequence to the corresponding smart control cabinet through the communication network of the distributed system; each smart control cabinet executing the corresponding control task according to the received control instruction sequence, and feeding back the operating status data to the distributed system in real time to update the global task conflict diagram of the next control cycle.

[0196] A control instruction sequence is the specific execution form of an optimized control task sequence, containing detailed operation commands that the intelligent control cabinet needs to execute. In this embodiment of the invention, the control instruction sequence consists of the following parts: instruction identifier, execution timestamp, operation type, operation parameters, and completion condition. The instruction identifier uniquely identifies an instruction, the execution timestamp specifies the execution time of the instruction, the operation type defines the specific behavior of the instruction (such as starting the device, adjusting parameters, or shutting down the device), the operation parameters provide the specific parameter values ​​required for instruction execution, and the completion condition defines the criteria for determining the completion of instruction execution.

[0197] In this embodiment of the invention, the process of generating a control instruction sequence includes: first, extracting the execution time and task attributes of each task from the optimized control task sequence; then, querying the instruction template library according to the task attributes to obtain the corresponding operation type and operation parameter format; and finally, filling in the specific parameter values ​​and execution timestamp to generate a complete control instruction sequence.

[0198] In one implementation of this invention, the control commands are represented in JSON format.

[0199] The control command sequence is sent to the corresponding smart control cabinet through the communication network of the distributed system. The communication network of the distributed system is the data transmission channel connecting the various smart control cabinets and the central control unit, and typically uses industrial Ethernet, wireless networks, or dedicated communication protocols. In this embodiment of the invention, the communication network adopts a secure, low-latency, and highly reliable communication mechanism to ensure that the control commands can be accurately and timely transmitted to each smart control cabinet.

[0200] In this embodiment of the invention, the communication protocol adopts industrial IoT standard protocols such as MQTT or OPCUA, supporting publish / subscribe and request / response modes to adapt to communication needs in different scenarios. Data encryption and authentication mechanisms are employed during communication to ensure security and reliability.

[0201] Each smart control cabinet executes the corresponding control task based on the received sequence of control commands. The smart control cabinet has a built-in control command parsing engine and task execution manager, capable of parsing the received control commands and executing the corresponding operations according to the specified time and order. During execution, the smart control cabinet monitors the task's execution status to ensure the task proceeds as planned and handles any possible anomalies.

[0202] In this embodiment of the invention, the task execution manager of the intelligent control cabinet adopts a real-time operating system and a priority queue management mechanism, which can handle concurrent execution of multiple tasks and task priority scheduling. For high-priority or time-critical tasks, the system will allocate more computing resources and higher execution priority to ensure that these tasks can be completed on time.

[0203] While executing control tasks, the intelligent control cabinet also feeds back operational status data to the distributed system in real time to update the global task conflict diagram for the next control cycle. Operational status data includes task execution progress, resource usage, and equipment operating parameters; this data is crucial for evaluating system performance and optimizing task scheduling.

[0204] In this embodiment of the invention, the feedback of operational status data adopts a combination of timed reporting and event triggering: timed reporting refers to reporting basic status data once every fixed time interval (e.g., 1 second); event triggering refers to immediately reporting relevant data when an important event occurs (e.g., task completion, resource shortage, abnormal situation, etc.). This method can ensure the real-time performance of status data while reducing unnecessary communication overhead.

[0205] The distributed system updates the global task conflict graph based on the received runtime status data, providing a basis for task scheduling and optimization in the next control cycle. The update process is a dynamic adjustment process; the system adjusts the edge weights and node attributes in the conflict graph based on the latest status data and execution results, ensuring that the conflict graph accurately reflects the current task conflict status of the system.

[0206] In this embodiment of the invention, the global task conflict graph is updated using an incremental update strategy, updating only the changed parts instead of rebuilding the entire conflict graph, thereby improving the system's response speed and efficiency. During the update process, the system focuses on tasks whose execution does not match expectations, analyzes the causes of conflicts, and adjusts them in the next optimization.

[0207] The above describes a distributed control method for an AI smart control cabinet in an embodiment of this application. The following describes a distributed control system for an AI smart control cabinet in an embodiment of this application. This system is used to implement the above-described distributed control method for the AI ​​smart control cabinet. Please refer to... Figure 2One embodiment of the distributed control system for an AI smart control cabinet in this application includes: a distributed management center, which connects to the smart control cabinet through a distributed communication network to realize the real-time transmission of control commands and status data;

[0208] The distributed management center includes:

[0209] The data acquisition module is used to acquire the operating status data and control task data of each smart control cabinet in each control cycle;

[0210] The task priority analysis module is used to construct a task priority vector for each smart control cabinet in each control cycle based on the operating status data and control task data.

[0211] The conflict graph construction module is used to generate a global task conflict graph for the distributed system based on the task priority vectors of all smart control cabinets within the same control cycle.

[0212] The conflict analysis module is used to obtain the probability of task conflict and the order of task execution for each smart control cabinet within the same control cycle based on the global task conflict diagram.

[0213] The task scheduling module is used to adjust the control task execution strategy of each smart control cabinet based on the task conflict probability and the task execution order, so as to obtain the optimized control task sequence of each smart control cabinet.

[0214] The collaborative control module is used to control the distributed collaborative operation of each smart control cabinet in the next control cycle according to the optimized control task sequence;

[0215] The various modules within the distributed management center are connected via wired and / or wireless means to enable data transmission between modules.

[0216] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0217] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0218] In the description of this invention, it should be understood that the terms "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0219] In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0220] In the description of this invention, "several" means one or more, and "a large number" means two or more.

[0221] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0222] All formulas in this manual are dimensionless and calculated numerically. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0223] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A distributed control method for an AI-powered smart control cabinet, characterized in that, include: Acquire the operating status data and control task data of each smart control cabinet in each control cycle; Based on the operational status data and the control task data, construct a task priority vector for each smart control cabinet in each control cycle; A global task conflict diagram is generated based on the task priority vector of all intelligent control cabinets within the same control cycle. Based on the global task conflict diagram, obtain the task conflict probability and task execution order of each smart control cabinet in the same control cycle; Based on the task conflict probability and the task execution order, the control task execution strategy of each smart control cabinet is adjusted to obtain an optimized control task sequence for each smart control cabinet. This includes: determining the task adjustment weight of each smart control cabinet within the same control cycle based on the task conflict probability; rearranging the control task data of each smart control cabinet according to the task execution order and the task adjustment weight to obtain a candidate control task sequence for each smart control cabinet; simulating the execution of the candidate control task sequence to obtain the overall system operating efficiency and conflict occurrence rate in the simulation execution results. Based on the overall system operating efficiency and the conflict occurrence rate, the candidate control task sequence is optimized to obtain the optimized control task sequence for each smart control cabinet. This includes: constructing an optimization function with the objectives of maximizing the overall system operating efficiency and minimizing the conflict occurrence rate; and using a genetic algorithm to iteratively optimize the candidate control task sequence to obtain the global optimal solution that satisfies the optimization function. The candidate control task sequence corresponding to the global optimal solution is used as the optimized control task sequence for each smart control cabinet. The process of rearranging the control task data for each smart control cabinet includes: For each smart control cabinet, a task description tuple is constructed from the control task data. The task description tuple includes the task identifier, original priority, execution duration, and resource requirements. The task adjustment weights are applied to the original priorities in the task description tuple to calculate the weighted priority value. A sequence constraint matrix is ​​constructed based on the task execution order to represent the sequential execution relationship between tasks; a priority-weighted directed acyclic graph is constructed based on the weighted priority value and the sequence constraint matrix. A topological sorting algorithm is applied to the priority-weighted directed acyclic graph to generate an initial sorting scheme; resource conflict detection is performed on the initial sorting scheme to identify task pairs that compete for resources within overlapping time intervals. For the identified task pairs, the weights are adjusted according to their respective tasks to resolve conflicts, and the relative execution positions are adjusted to obtain a sorting scheme after conflict resolution. The sorting scheme after conflict resolution is then mapped onto a time axis to generate a candidate control task sequence. The candidate control task sequence is optimized for compactness to reduce idle waiting time between tasks while keeping all sequence constraints unchanged. Based on the optimized control task sequence, control the distributed collaborative operation of each smart control cabinet in the next control cycle.

2. The distributed control method for an AI smart control cabinet according to claim 1, characterized in that, The construction of the task priority vector for each smart control cabinet in each control cycle includes: extracting the equipment load rate, operational stability index and fault risk value from the operational status data; Extract the task urgency, task complexity, and task dependency from the control task data; construct a task feature matrix for each smart control cabinet in each control cycle based on the equipment load rate, the operational stability index, the fault risk value, the task urgency, the task complexity, and the task dependency. The method for obtaining the operational stability index includes: obtaining a time series of operational status data for each smart control cabinet within the current control cycle; performing a Fourier transform on the time series to extract its frequency domain features; calculating the fluctuation amplitude and periodic rate of change of the time series based on the frequency domain features; and using the weighted sum of the fluctuation amplitude and the periodic rate of change as the operational stability index. Principal component analysis is performed on the task feature matrix to obtain the task priority vector of each smart control cabinet in each control cycle.

3. The distributed control method for an AI smart control cabinet according to claim 1, characterized in that, The generation of the global task conflict graph includes: Based on the task priority vectors of all smart control cabinets in the same control cycle, calculate the Euclidean distance between the task priority vectors of any two smart control cabinets, which is used as the task competition degree between the two smart control cabinets. Based on the task competitiveness and the task dependency relationship in the control task data, construct a directed graph of task conflicts among all smart control cabinets; Perform topological sorting on the directed graph of task conflicts to obtain the task conflict path of each smart control cabinet in the directed graph of task conflicts; weight and fuse the task conflict path with the task competition degree to generate a global task conflict graph.

4. The distributed control method for an AI smart control cabinet according to claim 1, characterized in that, The process of obtaining the task conflict probability and task execution order of each smart control cabinet within the same control cycle includes: Based on the global task conflict graph, extract the number of conflict nodes with other smart control cabinets in the task conflict path of each smart control cabinet; Based on the number of conflicting nodes and the degree of task competition, calculate the probability of task conflict for each smart control cabinet within the same control cycle; Based on the task conflict paths in the global task conflict graph, the task execution order of each smart control cabinet within the same control cycle is determined.

5. The distributed control method for an AI smart control cabinet according to claim 4, characterized in that, The step of determining the task execution order of each smart control cabinet within the same control cycle based on the task conflict paths in the global task conflict graph includes: A depth-first traversal is performed on each task conflict path in the global task conflict graph to generate a directed acyclic graph of task dependencies between the smart control cabinets. Based on the directed acyclic graph of the task dependencies, the task criticality index of each smart control cabinet is calculated. The task criticality index includes in-degree, out-degree and betweenness centrality. Construct a task execution priority matrix based on the task key indicators and the task priority vector; Apply the critical path algorithm to the task execution priority matrix to identify the critical chain of task execution; Based on the time constraints in the control task data of each smart control cabinet and the critical chain of task execution, a task execution time window is allocated to each smart control cabinet. Based on the task execution time window and the probability of task conflict, an adaptive time slicing strategy is adopted to determine the final task execution order of each smart control cabinet within the same control cycle.

6. The distributed control method for an AI smart control cabinet according to claim 3, characterized in that, The method for calculating the task competitiveness includes: Obtain the task priority vectors of any two smart control cabinets within the same control cycle; calculate the Euclidean distance between the task priority vectors as the initial competition degree. Based on the task dependencies in the control task data, determine whether there is a direct dependency between the two smart control cabinets; if there is a direct dependency, then positively weighted adjust the initial competitiveness; if there is no direct dependency, then negatively weighted adjust the initial competitiveness to obtain the task competitiveness.

7. A distributed control system for an AI-powered intelligent control cabinet, characterized in that, The distributed control method for the AI ​​smart control cabinet according to any one of claims 1 to 6 includes: a distributed management center, which connects to the smart control cabinet through a distributed communication network to realize the real-time transmission of control commands and status data; The distributed management center includes: The data acquisition module is used to acquire the operating status data and control task data of each smart control cabinet in each control cycle; The task priority analysis module is used to construct a task priority vector for each smart control cabinet in each control cycle based on the operating status data and the control task data. The conflict graph construction module is used to generate a global task conflict graph based on the task priority vector of all smart control cabinets in the same control cycle. The conflict analysis module is used to obtain the task conflict probability and task execution order of each smart control cabinet within the same control cycle based on the global task conflict diagram. The task scheduling module is used to adjust the control task execution strategy of each smart control cabinet based on the task conflict probability and the task execution order, so as to obtain the optimized control task sequence of each smart control cabinet. The collaborative control module is used to control the distributed collaborative operation of each smart control cabinet in the next control cycle according to the optimized control task sequence. The modules are connected to each other via wired and / or wireless means.

Images