Device group control-oriented machine room air conditioner alarm cooperative processing method and system

Abstract

The application provides a machine room air conditioner alarm cooperative processing method and system for device group control, relates to the technical field of control, and comprises the following steps: obtaining a plurality of air conditioner alarm information, performing spatial correlation analysis based on a device topology relationship, mapping the alarm information to a group control cooperative graph structure containing device nodes, alarm propagation edges and control dependency edges, identifying a root cause device node by using a reverse path backtracking algorithm, and generating a priority processing instruction. The application can accurately locate an alarm root cause, reduces a false alarm rate, and improves air conditioner system operation efficiency and energy utilization rate.

Description

Technical Field

[0001] This invention relates to the field of control technology, and in particular to a collaborative processing method and system for alarms of computer room air conditioning for equipment group control. Background Technology

[0002] Air conditioning equipment in data center server rooms is a critical infrastructure for ensuring the normal operation of information equipment, and its stable operation directly affects the reliability and energy efficiency of the data center. As data centers continue to expand, multiple air conditioning units are often deployed within a single server room, working collaboratively to create complex airflow organization and temperature field distribution. These units interact with each other through supply and return air systems, forming a tightly coupled spatial network. In actual operation, server room air conditioning systems frequently generate various alarms, such as temperature exceeding limits, abnormal airflow, and pressure fluctuations. These alarms are crucial for the timely detection and resolution of equipment failures.

[0003] Currently, most data center air conditioning alarm handling systems primarily adopt an independent processing mode, treating each air conditioning unit as an independent entity for monitoring and alarm processing. This approach typically triggers alarms based on fixed thresholds and then processes them according to alarm level or time sequence.

[0004] Existing technologies lack in-depth analysis of the spatial correlation between multiple air conditioning devices in a computer room, and cannot effectively identify the fault propagation and alarm cascading effects generated by airflow paths between devices. As a result, when dealing with alarms, we often only focus on the symptoms and ignore the root cause. Summary of the Invention

[0005] This invention provides a collaborative processing method and system for air conditioning alarms in computer rooms for group control of equipment, which can solve the problems in the prior art.

[0006] A first aspect of this invention provides a collaborative processing method for alarms in a computer room air conditioning system for group control of equipment, comprising:

[0007] The alarm information generated by multiple air conditioning devices in the computer room within the current time window is obtained. Based on the preset device topology relationship, the spatial correlation analysis of the alarm information is performed to obtain an alarm set with spatial coupling characteristics. The device topology relationship includes the supply air path dependency relationship and return air path dependency relationship between devices.

[0008] Based on the device identifier in the alarm information and the spatial coupling feature, the alarm information is mapped to a pre-constructed device group control collaborative graph structure. The device group control collaborative graph structure includes device nodes, alarm propagation edges, and control dependency edges between devices. The weight of the alarm propagation edge is determined by the airflow influence degree between devices and the alarm timing correlation degree.

[0009] Based on the device group control collaborative graph structure, a reverse path tracing algorithm is used to identify the root cause device node that causes the alarm set. According to the root cause device node and its associated control dependency edge, a priority processing instruction is generated for the root cause device node. The priority processing instruction includes device control parameter adjustment actions and alarm suppression strategies. The priority processing instruction is then sent to the air conditioning equipment corresponding to the root cause device node.

[0010] Based on a preset device topology, spatial correlation analysis is performed on the alarm information to obtain an alarm set with spatial coupling characteristics, including:

[0011] Based on the device identifier in the alarm information, the spatial location coordinates and airflow direction vector of the device corresponding to each alarm information are extracted from the device topology relationship. Combined with the alarm timestamp, the alarm timing difference between adjacent devices is calculated to obtain an alarm spatiotemporal feature matrix that includes spatial distance features and timing interval features.

[0012] Based on the supply air path dependency and the return air path dependency, airflow conduction path matching is performed on each alarm information in the alarm spatiotemporal feature matrix, and the spatial coupling degree between devices on the same airflow conduction path is calculated. The spatial coupling degree is determined by the connectivity of the airflow conduction path and the spatial distance feature.

[0013] Alarm information whose spatial coupling exceeds a preset coupling threshold is grouped into the same alarm set to obtain the alarm set with spatial coupling characteristics.

[0014] Based on the supply air path dependency and the return air path dependency, airflow conduction path matching is performed on each alarm information in the alarm spatiotemporal feature matrix, and the spatial coupling degree between devices on the same airflow conduction path is calculated, including:

[0015] Based on the supply air path dependency and the return air path dependency, a directed graph of airflow conduction paths is constructed. The nodes of the directed graph of airflow conduction paths correspond to the device identifiers in the alarm spatiotemporal feature matrix. The directed edges of the directed graph of airflow conduction paths represent the airflow conduction relationship in the supply air direction or the return air direction. The edge weight of the directed edge is determined by the consistency degree of the airflow direction vector and the reciprocal of the spatial distance feature.

[0016] For each pair of alarm messages, a connectivity test is performed on the directed graph of the airflow conduction path to determine whether a directed connected path exists between the device nodes corresponding to the two alarm messages;

[0017] If it exists, the cumulative attenuation calculation is performed on the edge weights of all directed edges on the directed connected path to obtain the spatial coupling degree of the device node pair. The cumulative attenuation calculation is achieved by weighted summation of the edge weights of each directed edge on the path and applying a path length attenuation factor. The path length attenuation factor decreases as the number of nodes contained in the directed connected path increases.

[0018] Based on the device group control collaborative graph structure, the root cause device node leading to the alarm set is identified using a reverse path tracing algorithm, including:

[0019] Traverse all device nodes in the device group control collaboration graph structure, and based on the alarm information in the alarm set, mark the device nodes that generate alarms as alarm nodes and assign them an initial alarm propagation contribution, and mark the device nodes that do not generate alarms as candidate root cause nodes;

[0020] The system iterates along the reverse direction of the control dependency edges in the device group control collaboration graph structure. For each alarm node, it identifies the upstream device node that is pointed to by the control dependency edge, and propagates the alarm propagation contribution of the alarm node to the upstream device node in reverse according to the weight of the alarm propagation edge. The reverse propagation is achieved by combining the alarm propagation contribution with the attenuation coefficient of the alarm propagation edge weight, so as to obtain the cumulative alarm propagation contribution of each upstream device node.

[0021] During the iterative traversal, only propagation paths that satisfy the control dependency edge directionality constraint are retained. The directionality constraint requires that the direction of the control dependency edge on the propagation path be consistent with the causal direction of alarm propagation.

[0022] When the iterative traversal terminates, the device node with the largest cumulative alarm propagation contribution is selected from the candidate root cause nodes as the root cause device node.

[0023] Based on the weight of the alarm propagation edge, the alarm propagation contribution of the alarm node is propagated back to the upstream device node, including:

[0024] The weights of the alarm propagation edge are decomposed into an airflow influence component and an alarm timing correlation component. The airflow influence component represents the intensity of the airflow transmission influence of the upstream device node on the alarm node, and the alarm timing correlation component represents the temporal correlation strength between the change in the operating state of the upstream device node and the alarm occurrence time of the alarm node.

[0025] For each incident alarm propagation edge of an alarm node, a nonlinear fusion calculation is performed on the airflow influence component and the alarm timing correlation component to obtain the comprehensive transmission coefficient of the incident alarm propagation edge. The nonlinear fusion calculation is achieved by multiplying the airflow influence component and the alarm timing correlation component and applying normalization processing.

[0026] The alarm propagation contribution of the alarm node is multiplied by the comprehensive transmission coefficient to obtain the contribution increment transmitted to the corresponding upstream device node through the incident alarm propagation edge;

[0027] The contribution increment is added to the current cumulative alarm propagation contribution of the corresponding upstream device node to complete the update of the cumulative alarm propagation contribution of the upstream device node.

[0028] Based on the root cause device node and its associated control dependency edges, priority processing instructions are generated for the root cause device node, including:

[0029] Starting from the root cause device node, a breadth-first traversal is performed along the positive direction of the control dependency edges in the device group control collaboration graph structure to identify all downstream device nodes directly or indirectly affected by the root cause device node, and to construct an influence domain topology subgraph containing the root cause device node and all downstream device nodes;

[0030] For each downstream device node in the influence domain topology subgraph, the control constraint conditions corresponding to the downstream device node are extracted from the edge attributes of the control-dependent edge.

[0031] The control constraints include the allowable adjustment range of the operating parameters of the downstream device node and the state switching timing requirements of the downstream device node. The adjustment range of the operating parameters is determined by the control strength component in the control dependency edge weights, and the state switching timing requirements are determined by the response delay component in the control dependency edge weights.

[0032] Based on the topological hierarchy of the influence domain topology subgraph, and in accordance with the control transmission sequence from the root cause device node to the downstream device node, a master control command is generated for the root cause device node, and a slave control command is generated for each downstream device node.

[0033] The method further includes:

[0034] The feasibility of the operation parameter adjustment amounts in the main control command and the coordinated adjustment amounts in the secondary control command is verified by substituting them into the control constraints.

[0035] When the adjustment amount is detected to exceed the adjustment range of the operating parameters or violate the state switching timing requirements, the excessive adjustment amount is reduced and corrected and redistributed to other device nodes in the influence domain topology subgraph to obtain optimized master control instructions and optimized slave control instructions that satisfy the control constraints. The optimized master control instructions are then output as the priority processing instructions.

[0036] A second aspect of this invention provides a collaborative processing system for alarms in a computer room air conditioning system for group control of equipment, comprising:

[0037] The first unit is used to acquire alarm information generated by multiple air conditioning devices in the computer room within the current time window, and to perform spatial correlation analysis on the alarm information based on the preset device topology relationship to obtain an alarm set with spatial coupling characteristics. The device topology relationship includes the supply air path dependency relationship and return air path dependency relationship between devices.

[0038] The second unit is used to map the alarm information to a pre-constructed device group control collaborative graph structure based on the device identifier in the alarm information and the spatial coupling feature. The device group control collaborative graph structure includes device nodes, alarm propagation edges, and control dependency edges between devices. The weight of the alarm propagation edge is determined by the airflow influence degree between devices and the alarm timing correlation degree.

[0039] The third unit is used to identify the root cause device node that causes the alarm set by using a reverse path tracing algorithm based on the device group control collaborative graph structure. Based on the root cause device node and its associated control dependency edge, it generates a priority processing instruction for the root cause device node. The priority processing instruction includes device control parameter adjustment actions and alarm suppression strategies. The priority processing instruction is then sent to the air conditioning equipment corresponding to the root cause device node.

[0040] A third aspect of the present invention,

[0041] An electronic device is provided, comprising:

[0042] processor;

[0043] Memory used to store processor-executable instructions;

[0044] The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0045] Fourth aspect of the embodiments of the present invention,

[0046] A computer-readable storage medium is provided, having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0047] The beneficial effects of this application are as follows:

[0048] This invention achieves intelligent collaborative processing of air conditioning alarms in computer rooms by using spatial correlation analysis based on device topology and device group control collaborative graph structure, effectively avoiding alarm storms and improving fault handling efficiency.

[0049] This invention introduces a topology analysis method that considers the dependence of supply and return air paths, and combines it with an alarm propagation edge weighting mechanism to accurately identify the root cause device node, thereby solving the problem of multi-device cascading alarms from the source and reducing the workload of operation and maintenance personnel.

[0050] The priority processing instructions provided by this invention include equipment control parameter adjustment and alarm suppression strategies, realizing intelligent hierarchical processing of alarms, reducing the number of invalid alarms, and improving the stability of the computer room environment and the operating efficiency of the air conditioning system through automated control. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating the collaborative processing method for alarms of computer room air conditioning for equipment group control according to an embodiment of the present invention.

[0052] Figure 2 This is a flowchart illustrating the process of using a reverse path tracing algorithm to identify the root cause device node that generates the alarm set. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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.

[0054] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0055] refer to Figure 1 and Figure 2 The present invention provides a collaborative alarm processing method for computer room air conditioning for equipment group control, comprising:

[0056] The alarm information generated by multiple air conditioning devices in the computer room within the current time window is obtained. Based on the preset device topology relationship, the spatial correlation analysis of the alarm information is performed to obtain an alarm set with spatial coupling characteristics. The device topology relationship includes the supply air path dependency relationship and return air path dependency relationship between devices.

[0057] Based on the device identifier in the alarm information and the spatial coupling feature, the alarm information is mapped to a pre-constructed device group control collaborative graph structure. The device group control collaborative graph structure includes device nodes, alarm propagation edges, and control dependency edges between devices. The weight of the alarm propagation edge is determined by the airflow influence degree between devices and the alarm timing correlation degree.

[0058] Based on the device group control collaborative graph structure, a reverse path tracing algorithm is used to identify the root cause device node that causes the alarm set. According to the root cause device node and its associated control dependency edge, a priority processing instruction is generated for the root cause device node. The priority processing instruction includes device control parameter adjustment actions and alarm suppression strategies. The priority processing instruction is then sent to the air conditioning equipment corresponding to the root cause device node.

[0059] In one optional implementation, spatial correlation analysis is performed on the alarm information based on a preset device topology to obtain an alarm set with spatial coupling characteristics, including:

[0060] Based on the device identifier in the alarm information, the spatial location coordinates and airflow direction vector of the device corresponding to each alarm information are extracted from the device topology relationship. Combined with the alarm timestamp, the alarm timing difference between adjacent devices is calculated to obtain an alarm spatiotemporal feature matrix that includes spatial distance features and timing interval features.

[0061] Based on the supply air path dependency and the return air path dependency, airflow conduction path matching is performed on each alarm information in the alarm spatiotemporal feature matrix, and the spatial coupling degree between devices on the same airflow conduction path is calculated. The spatial coupling degree is determined by the connectivity of the airflow conduction path and the spatial distance feature.

[0062] Alarm information whose spatial coupling exceeds a preset coupling threshold is grouped into the same alarm set to obtain the alarm set with spatial coupling characteristics.

[0063] Device topology is a digital representation of the spatial location and airflow conduction relationships of each device in a data center cooling system. This relationship includes each device's identifier, three-dimensional coordinate position, airflow direction vector, and supply and return air path dependencies. Alarm information includes at least the device identifier, alarm type, alarm level, and alarm timestamp.

[0064] In the spatial correlation analysis phase, all alarm information triggered within the last 24 hours is extracted from the alarm log database. For each alarm record, the spatial location information of the corresponding device is queried from the device topology database using the device identifier. Specifically, the X, Y, and Z coordinates of each alarm device, as well as the main airflow direction vector of that device, are extracted. Assume a data center has 15 alarm records within a specific time period, originating from air conditioning units numbered CRAC-01 to CRAC-05 and server racks numbered RACK-01 to RACK-10.

[0065] For every two devices with alarms, the spatial distance between them is calculated using the three-dimensional Euclidean distance formula, which is the straight-line distance between two points. For example, if the coordinates of CRAC-01 are (10,5,0) and the coordinates of RACK-03 are (12,8,0), then the spatial distance between them is 5 meters. Simultaneously, the timestamps of each alarm are extracted, and the timing difference between any two alarms is calculated in seconds. For example, if the alarm time of CRAC-01 is 2023-07-15 14:30:25 and the alarm time of RACK-03 is 2023-07-15 14:33:42, then the timing difference is 197 seconds.

[0066] All alarm spatial location coordinates, airflow direction, and time sequence differences between alarms are organized into an alarm spatiotemporal feature matrix. This matrix is ​​a multi-dimensional data structure, where each row represents a pair of alarm combinations, and columns contain device identifiers, spatial distance values, time sequence interval values, and other relevant attributes.

[0067] Based on predefined supply air path dependencies and return air path dependencies, airflow conduction path matching analysis is performed on each alarm device in the alarm spatiotemporal feature matrix. The supply air path dependency describes the path network of cold air flowing from the air conditioning unit to the server rack, while the return air path dependency describes the path network of hot air returning from the server rack to the air conditioning unit.

[0068] For any two alarm devices, check whether they are on the same airflow path. Specifically, this is achieved using a path lookup algorithm in a graph data structure to determine if airflow connectivity exists between the two devices. For example, if CRAC-01's cool air is directly supplied to RACK-01, RACK-02, and RACK-03, while RACK-04 receives cool air from CRAC-02, then CRAC-01 and RACK-03 are on the same airflow path, while CRAC-01 and RACK-04 are not.

[0069] For device pairs confirmed to be located on the same airflow path, their spatial coupling degree is further calculated. Spatial coupling degree is a comprehensive indicator that reflects the degree of correlation between two devices in space and airflow conduction. Specifically, the connectivity strength of the airflow conduction path is determined, and this connectivity strength is related to the number of devices on the path and the complexity of the connections. For example, the connectivity strength of directly connected devices is 1.0, the connectivity strength of devices connected through one intermediate device is 0.8, the connectivity strength of devices connected through two intermediate devices is 0.6, and so on.

[0070] Subsequently, the connectivity strength is combined with the spatial distance characteristics between the devices to calculate the final spatial coupling degree. Specifically, the spatial coupling degree is equal to the connectivity strength multiplied by a decreasing function of the spatial distance. When the distance between the two devices is 0, the decreasing function value is 1; as the distance increases, the function value gradually decreases. For example, the connectivity strength between CRAC-01 and RACK-03 is 1.0, the spatial distance is 5 meters, the corresponding decreasing function value is 0.7, and the final spatial coupling degree is 0.7.

[0071] The system has a preset spatial coupling threshold of 0.5. When the spatial coupling between two devices exceeds this threshold, the alarms from both devices are grouped into the same alarm set. In this way, alarm groups that are causally related due to airflow conduction can be identified.

[0072] Through the above implementation process, alarm sets with spatial coupling characteristics can be extracted from a large number of scattered alarm messages. These alarm sets represent groups of devices that are closely related in terms of physical space and airflow transmission, providing important evidence for subsequent root cause analysis. For example, in the example scenario, alarms CRAC-01, RACK-01, RACK-02, and RACK-03 are identified as forming an alarm set, indicating that these devices share a common cause of failure or a failure propagation relationship.

[0073] In one optional implementation, based on the supply air path dependency and the return air path dependency, airflow conduction path matching is performed on each alarm information in the alarm spatiotemporal feature matrix, and the spatial coupling degree between devices on the same airflow conduction path is calculated, including:

[0074] Based on the supply air path dependency and the return air path dependency, a directed graph of airflow conduction paths is constructed. The nodes of the directed graph of airflow conduction paths correspond to the device identifiers in the alarm spatiotemporal feature matrix. The directed edges of the directed graph of airflow conduction paths represent the airflow conduction relationship in the supply air direction or the return air direction. The edge weight of the directed edge is determined by the consistency degree of the airflow direction vector and the reciprocal of the spatial distance feature.

[0075] For each pair of alarm messages, a connectivity test is performed on the directed graph of the airflow conduction path to determine whether a directed connected path exists between the device nodes corresponding to the two alarm messages;

[0076] If it exists, the cumulative attenuation calculation is performed on the edge weights of all directed edges on the directed connected path to obtain the spatial coupling degree of the device node pair. The cumulative attenuation calculation is achieved by weighted summation of the edge weights of each directed edge on the path and applying a path length attenuation factor. The path length attenuation factor decreases as the number of nodes contained in the directed connected path increases.

[0077] Based on the acquired supply and return air path dependencies, a directed graph of airflow conduction paths is constructed. In this directed graph, nodes correspond to device identifiers appearing in the alarm spatiotemporal feature matrix, such as air conditioner A and temperature sensor B. Directed edges represent the directional relationships of airflow conduction, including the supply or return air direction. For example, a directed edge from air conditioner A to temperature sensor B indicates that the airflow from air conditioner A affects the environment of sensor B.

[0078] The calculation of the edge weight of a directed edge combines the consistency of the airflow direction vector with the reciprocal of the spatial distance characteristic. Specifically, for a directed edge connecting device i and device j, its edge weight can be determined as follows: First, calculate the cosine of the angle between the airflow direction vector of device i and the spatial position vector from device i to device j. The closer this value is to 1, the more consistent the airflow direction is with the direction of the line connecting the two devices. Then, calculate the reciprocal of the spatial distance between the two devices. The closer the distance, the larger this value. Finally, weight the two characteristic values ​​to obtain the edge weight. For example, if the angle between the airflow direction of air conditioner A and the direction of the line connecting air conditioner A to sensor B is 30 degrees, and the distance between the two devices is 5 meters, then the consistency is approximately 0.866, the reciprocal of the distance is 0.2, and the combined edge weight can be set as 0.866 × 0.7 + 0.2 × 0.3 = 0.6662.

[0079] After constructing the directed graph of airflow conduction paths, connectivity detection is performed on each pair of alarm messages in the alarm spatiotemporal feature matrix to determine whether a directed connected path exists between the device nodes corresponding to the two alarm messages. This step can be implemented using a depth-first search or breadth-first search algorithm. For example, if alarm messages for device C and device E exist in the matrix, all possible paths from C to E or from E to C will be searched in the directed graph.

[0080] When a directed path is confirmed between two device nodes, the spatial coupling degree between these two nodes is calculated. The spatial coupling degree is obtained by cumulatively attenuating the edge weights of each directed edge on the path. Specifically, this involves traversing all edges on the directed path from the start node to the end node, collecting the edge weight of each edge, and then applying a path length attenuation factor.

[0081] The path length attenuation factor is designed as a function that decreases as the number of nodes in the directed connected path increases. For example, for a path of length n (containing n+1 nodes), an attenuation factor of 1 / (1+α(n-1)) can be used, where α is the attenuation rate parameter, typically between 0.1 and 0.5. This design ensures that the longer the path, the more significant the cumulative attenuation effect, reflecting the physical characteristic that the airflow conduction effect weakens with propagation distance.

[0082] Let's illustrate the calculation process with a specific example: Assume a data center has alarm devices A, B, C, D, and E. In the directed graph of airflow transmission paths, there exist paths A→B→C→D and A→E→D. We need to calculate the spatial coupling degree between device A and device D. First, find the two paths from A to D in the directed graph: A→B→C→D (path 1) and A→E→D (path 2).

[0083] For path 1, assuming the edge weights of A→B, B→C, and C→D are 0.8, 0.7, and 0.6 respectively, the path length is 3 (containing 4 nodes), and the attenuation factor is 1 / (1+0.2×(3-1))=0.71. The cumulative spatial coupling degree is calculated to be (0.8+0.7+0.6)×0.71=1.491.

[0084] For path 2, assume the edge weights of A→E and E→D are 0.75 and 0.65 respectively, the path length is 2 (containing 3 nodes), and the attenuation factor is 1 / (1+0.2×(2-1))=0.83. The cumulative spatial coupling degree is calculated to be (0.75+0.65)×0.83=1.162.

[0085] Comparing the spatial coupling values ​​of the two paths, the larger value of 1.491 is selected as the final spatial coupling between device A and device D. This indicates that the airflow conduction from device A to device D has a stronger influence, and the alarms of the two devices are highly correlated.

[0086] The above methods can effectively identify equipment alarm correlations caused by airflow conduction, providing data center operations and maintenance personnel with more accurate fault diagnosis basis, reducing misjudgments and omissions, and improving operation and maintenance efficiency. Meanwhile, the quantitative calculation of spatial coupling degree also provides important feature inputs for subsequent alarm correlation analysis and root cause localization.

[0087] In one optional implementation, based on the device group control collaborative graph structure, a reverse path tracing algorithm is used to identify the root cause device node that leads to the alarm set, including:

[0088] Traverse all device nodes in the device group control collaboration graph structure, and based on the alarm information in the alarm set, mark the device nodes that generate alarms as alarm nodes and assign them an initial alarm propagation contribution, and mark the device nodes that do not generate alarms as candidate root cause nodes;

[0089] The system iterates along the reverse direction of the control dependency edges in the device group control collaboration graph structure. For each alarm node, it identifies the upstream device node that is pointed to by the control dependency edge, and propagates the alarm propagation contribution of the alarm node to the upstream device node in reverse according to the weight of the alarm propagation edge. The reverse propagation is achieved by combining the alarm propagation contribution with the attenuation coefficient of the alarm propagation edge weight, so as to obtain the cumulative alarm propagation contribution of each upstream device node.

[0090] During the iterative traversal, only propagation paths that satisfy the control dependency edge directionality constraint are retained. The directionality constraint requires that the direction of the control dependency edge on the propagation path be consistent with the causal direction of alarm propagation.

[0091] When the iterative traversal terminates, the device node with the largest cumulative alarm propagation contribution is selected from the candidate root cause nodes as the root cause device node.

[0092] Traversing all device nodes in the device group control collaboration graph structure, taking a network with 10 device nodes as an example, when alarm information is detected in 3 of these nodes (device A, device C, and device F), these 3 nodes are marked as alarm nodes and assigned initial alarm propagation contribution values. For example, based on the severity of the alarm, device A is assigned an alarm contribution of 0.8, device C an alarm contribution of 0.6, and device F an alarm contribution of 0.7. The remaining 7 device nodes that did not generate alarms (device B, device D, device E, device G, device H, device I, and device J) are marked as candidate root cause nodes, and their initial alarm propagation contribution is set to 0.

[0093] The iterative traversal begins in the reverse direction of the control dependency edges in the device group control collaboration graph structure. For example, device A is detected to have control dependency edges from devices B and D, with weights of 0.9 and 0.5 respectively; device C has a control dependency edge from device D with a weight of 0.8; and device F has a control dependency edge from device E with a weight of 0.7. For each alarm node, the upstream device node that points to the alarm node through the control dependency edge is identified.

[0094] For alarm node device A, devices B and D are identified as its upstream nodes. The alarm propagation contribution of device A (0.8) is transmitted to devices B and D through a reverse propagation mechanism. Assuming an attenuation coefficient of 0.9, the contribution increment obtained by device B is 0.8 × 0.9 × 0.9 = 0.648, and the contribution increment obtained by device D is 0.8 × 0.9 × 0.5 = 0.36.

[0095] For alarm node device C, device D is identified as its upstream node, and the alarm propagation contribution of device C (0.6) is passed back to device D. Using the same attenuation coefficient of 0.9, the contribution increment obtained by device D is 0.6 × 0.9 × 0.8 = 0.432.

[0096] For alarm node device F, device E is identified as its upstream node, and the alarm propagation contribution of device F (0.7) is passed back to device E. Using the same attenuation coefficient of 0.9, the contribution increment obtained by device E is 0.7 × 0.9 × 0.7 = 0.441.

[0097] After this iteration, device B's cumulative alarm propagation contribution is 0.648, device D's is 0.36 + 0.432 = 0.792, and device E's is 0.441. The next iteration continues, checking whether these nodes that have gained contribution points still have upstream nodes.

[0098] Suppose we find that device B has a control dependency edge from device G with a weight of 0.6; device D has control dependency edges from devices G and H with weights of 0.7 and 0.4 respectively; and device E has a control dependency edge from device H with a weight of 0.8. The contribution will continue to be passed upstream using the same mechanism.

[0099] During the propagation process, the directional constraints of control dependency edges must be strictly adhered to, ensuring that the alarm propagation path is consistent with the causal direction of the control dependency. For example, if there is a control dependency edge from device I to device J, but in the actual network topology, the alarm propagation direction is from device J to device I, which is opposite to the direction of the control dependency, then this propagation path will be excluded.

[0100] The iterative process continues until no new upstream nodes are discovered or the contribution values ​​of all propagated alarms are less than a preset threshold (e.g., 0.01). In this example, after multiple iterations, the cumulative alarm propagation contribution of device G eventually reaches 1.253, and the cumulative alarm propagation contribution of device H reaches 0.896.

[0101] After the iteration traversal terminates, the device node with the largest cumulative alarm propagation contribution is selected from the candidate root cause nodes (device B, device D, device E, device G, device H, device I, device J) as the root cause device node. In this example, device G has the highest cumulative alarm propagation contribution (1.253), and is therefore identified as the root cause device node.

[0102] This root cause analysis method, based on reverse path tracing, effectively traces the source of a fault by quantifying the influence relationships between devices and combining them with actual alarm conditions. Especially in complex network environments, multiple alarms may be caused by the same root cause, and this method can accurately identify this root cause rather than simply addressing surface phenomena, thereby improving the accuracy and efficiency of fault diagnosis.

[0103] In one optional implementation, the reverse propagation of the alarm node's alarm propagation contribution to the upstream device node according to the weight of the alarm propagation edge includes:

[0104] The weights of the alarm propagation edge are decomposed into an airflow influence component and an alarm timing correlation component. The airflow influence component represents the intensity of the airflow transmission influence of the upstream device node on the alarm node, and the alarm timing correlation component represents the temporal correlation strength between the change in the operating state of the upstream device node and the alarm occurrence time of the alarm node.

[0105] For each incident alarm propagation edge of an alarm node, a nonlinear fusion calculation is performed on the airflow influence component and the alarm timing correlation component to obtain the comprehensive transmission coefficient of the incident alarm propagation edge. The nonlinear fusion calculation is achieved by multiplying the airflow influence component and the alarm timing correlation component and applying normalization processing.

[0106] The alarm propagation contribution of the alarm node is multiplied by the comprehensive transmission coefficient to obtain the contribution increment transmitted to the corresponding upstream device node through the incident alarm propagation edge;

[0107] The contribution increment is added to the current cumulative alarm propagation contribution of the corresponding upstream device node to complete the update of the cumulative alarm propagation contribution of the upstream device node.

[0108] This implementation provides a method for reverse propagation of alarm propagation contribution based on alarm propagation edge weights. This method is applicable to root cause localization of equipment failures in data center air conditioning systems, and can accurately trace the upstream root cause device leading to the alarm by analyzing airflow conduction relationships and alarm timing correlations.

[0109] In data center air conditioning systems, alarm propagation graphs are used to characterize the airflow relationships between devices. An alarm propagation graph includes device nodes and alarm propagation edges, where the edges represent the path of influence from upstream devices to downstream devices. When an alarm occurs at a device node, it is necessary to determine which upstream devices are likely the root cause of the alarm. This implementation identifies the most likely root cause device by propagating the contribution of the alarm node backward along the alarm propagation edges to the upstream devices.

[0110] For the weight decomposition of alarm propagation edges, the weight of each alarm propagation edge is divided into two key components: the airflow influence component and the alarm timing correlation component. The airflow influence component reflects the intensity of the airflow transmission influence of upstream equipment on downstream equipment, and can be calculated through airflow models or historical operating data. For example, the airflow influence component of an air conditioning unit A on the downstream hotspot area B is 0.75, indicating that the change in the operating status of A has a strong influence on the temperature of area B. The alarm timing correlation component reflects the degree of temporal correlation between the change in the status of upstream equipment and the occurrence time of the alarm of downstream equipment, and is calculated by analyzing the time relationship between the change in the status of equipment and the triggering of the alarm. For example, if the fan speed of upstream equipment C changes significantly 10 minutes before the alarm of downstream equipment D, the alarm timing correlation component between them is 0.85, indicating that the two have a strong temporal correlation.

[0111] For each incident alarm propagation edge of an alarm node, a nonlinear fusion calculation is needed to obtain the comprehensive transmission coefficient by combining the airflow influence component and the alarm timing correlation component. Specifically, this is achieved by nonlinearly combining the two components through a product operation and then applying normalization. For example, if the airflow influence component of an incident alarm propagation edge is 0.8 and the alarm timing correlation component is 0.6, then its initial product is 0.48. Assuming the current alarm node has three incident edges with initial products of 0.48, 0.32, and 0.2 respectively, the normalized comprehensive transmission coefficients are 0.48, 0.32, and 0.2 respectively. Normalization ensures that the sum of the comprehensive transmission coefficients of all incident edges is 1, maintaining the total conservation of contribution during the backpropagation process.

[0112] When calculating the contribution increment, the alarm propagation contribution of the alarm node is multiplied by the overall propagation coefficient. Assuming an alarm node has an alarm propagation contribution of 100, and the overall propagation coefficients for the three incident edges are 0.48, 0.32, and 0.2, then the contribution increments propagated to upstream devices through these three edges are 48, 32, and 20, respectively. This indicates that the first upstream device has the largest contribution to the current alarm and is most likely the root cause of the fault.

[0113] Finally, the calculated contribution increment is added to the current cumulative alarm propagation contribution of the corresponding upstream device node. For example, if the current cumulative alarm propagation contribution of an upstream device node is 25, and the contribution increment received through the incident alarm propagation edge is 48, then the updated cumulative alarm propagation contribution is 73. After the system completes the reverse contribution propagation of the entire alarm propagation graph, the device node with the highest cumulative alarm propagation contribution is identified as the most likely root cause of the fault.

[0114] In practical applications, this method can handle complex alarm propagation scenarios. For example, a data center deploys 10 air conditioning units and 200 temperature sensors, with 5 temperature sensors simultaneously triggering high-temperature alarms. By constructing an alarm propagation graph, the airflow influence component and alarm timing correlation component between each alarm sensor and the upstream air conditioning equipment are analyzed. After reverse propagation calculation of contribution, it is found that the cumulative alarm propagation contribution of air conditioning unit G reaches 285, far higher than other air conditioning units (the second highest is air conditioning unit H, with a contribution of 127). Therefore, air conditioning unit G is determined to be the most likely root cause device of the failure.

[0115] This method can also handle complex situations involving multi-level propagation. When an alarm propagates from downstream to upstream devices, the cumulative contribution of the upstream devices is further passed on to even more upstream devices. Through this multi-level propagation mechanism, even if there are multiple intermediate devices between the root cause of the fault and the alarm node, the system can still accurately trace back to the true source of the fault. For example, in a fault analysis, the system, through three levels of reverse propagation, ultimately pinpointed the root cause of abnormal temperatures in multiple areas to a control valve failure in a fresh air handling unit, rather than a directly connected air conditioning unit.

[0116] The advantage of this implementation method is that it simultaneously considers the influence of physical airflow and temporal correlation, and balances the influence of the two through a nonlinear fusion mechanism, thereby improving the accuracy and interpretability of fault root cause localization.

[0117] In one optional implementation, generating priority processing instructions for the root cause device node based on the root cause device node and its associated control dependency edges includes:

[0118] Starting from the root cause device node, a breadth-first traversal is performed along the positive direction of the control dependency edges in the device group control collaboration graph structure to identify all downstream device nodes directly or indirectly affected by the root cause device node, and to construct an influence domain topology subgraph containing the root cause device node and all downstream device nodes;

[0119] For each downstream device node in the influence domain topology subgraph, the control constraint conditions corresponding to the downstream device node are extracted from the edge attributes of the control-dependent edge.

[0120] The control constraints include the allowable adjustment range of the operating parameters of the downstream device node and the state switching timing requirements of the downstream device node. The adjustment range of the operating parameters is determined by the control strength component in the control dependency edge weights, and the state switching timing requirements are determined by the response delay component in the control dependency edge weights.

[0121] Based on the topological hierarchy of the influence domain topology subgraph, and in accordance with the control transmission sequence from the root cause device node to the downstream device node, a master control command is generated for the root cause device node, and a slave control command is generated for each downstream device node.

[0122] In a collaborative device control system, once the root cause device node is identified, targeted processing instructions need to be generated to minimize system losses and achieve efficient recovery. The core of this method is to determine precise control strategies through in-depth analysis of the control dependencies between devices.

[0123] For example, starting with the identified root cause device node, a breadth-first traversal operation is performed along the positive direction of the control dependency edges in the device group control collaboration graph structure. This traversal operation begins from the root cause device node and sequentially visits the first-level downstream device nodes directly connected via control dependency edges, adding these first-level downstream device nodes to the queue to be visited. Subsequently, for each first-level downstream device node in the queue, the second-level downstream device nodes are visited along its radiating control dependency edges, and the second-level downstream device nodes are added to the queue. This process is continued layer by layer until all device nodes reachable from the root cause device node via control dependency edge paths have been traversed. During the traversal, the node identifier of each visited device node and its level depth relative to the root cause device node in the topology are recorded. The level depth is determined by the number of control dependency edges traversed along the traversal path. After the traversal is complete, a set of all downstream device nodes directly or indirectly controlled by the root cause device node is obtained.

[0124] Based on the downstream device node set obtained through traversal, an influence domain topology subgraph is constructed. This influence domain topology subgraph includes the root cause device node and all downstream device nodes, and retains the control dependency edges between these device nodes and their complete edge attribute information. Specifically, the root cause device node is used as the root node of the influence domain topology subgraph, and downstream device nodes are organized hierarchically according to their layer depth. Device nodes at the same layer depth are grouped into the same topology layer, and different topology layers are connected by control dependency edges. For each control dependency edge retained in the influence domain topology subgraph, the weight information of the edge is extracted and saved. This weight information includes a control strength component representing the control capability of the upstream device node over the downstream device node, and a response delay component representing the time required for the control command to be transmitted from the upstream device node to the downstream device node. Through this construction process, a device influence range topology structure centered on the root cause device node and organized according to the control transmission hierarchy is formed.

[0125] For each downstream device node in the influence domain topology subgraph, regulatory constraints are extracted from the edge attributes of the incident control dependency edges connecting that downstream device node. For any downstream device node, the regulatory constraints include two dimensions: the magnitude of operating parameter adjustment and the state transition timing requirements. The magnitude of operating parameter adjustment is extracted by reading the control strength component in the weights of the corresponding incident control dependency edges of the downstream device node. The larger the value of this control strength component, the stronger the control influence of the upstream device node on the downstream device node, and correspondingly, the larger the allowed magnitude of operating parameter adjustment for the downstream device node. The magnitude of operating parameter adjustment is specifically quantified as the maximum percentage range within which the current operating parameter value of the downstream device node can change, and this percentage range is positively correlated with the control strength component. The state transition timing requirements are extracted by reading the response delay component in the weights of the corresponding incident control dependency edges of the downstream device node. This response delay component reflects the time required for the control command to be transmitted from the upstream device node to the downstream device node and take effect. The state transition timing requirements are specifically quantified as the minimum response interval that the downstream device node must meet after receiving the regulatory command. This interval ensures that the device has sufficient time to complete the state transition without control conflict. By performing this extraction operation on all downstream device nodes in the influence domain topology subgraph, the set of control constraints for each downstream device node can be obtained.

[0126] Based on the topological hierarchy of the influence domain topology subgraph, control commands are generated for each device node sequentially, following the control transmission order from the root cause device node to downstream device nodes. First, a master control command is generated for the root cause device node, containing adjustments to its operating status. The generation of the master control command determines specific control actions based on the device type and alarm characteristics of the root cause device node. These actions include adjustments to operating parameters and state mode switching targets. The operating parameter adjustment amount is determined based on the alarm severity and historical operating data of the root cause device node. When the alarm severity is high, the operating parameter adjustment amount is set to a larger value to quickly eliminate the fault; when the alarm severity is low, the operating parameter adjustment amount is set to a smaller value for a smooth transition. The state mode switching target is determined based on the alarm type and the functional positioning of the root cause device node, ensuring that the switched state mode can directly eliminate the root cause of the alarm.

[0127] After generating the master control command, slave control commands are generated layer by layer for downstream device nodes according to the topological hierarchy of the influence domain topology subgraph, starting from the first level. For downstream device nodes in the first level, the required coordinated adjustment amount is calculated based on the expected state change after the execution of the master control command of the root device node, combined with the control dependency edge weights connecting the downstream device node and the root device node. The calculation of the coordinated adjustment amount considers the degree of influence of the master control command on the operating state of the downstream device node, which is determined by the control strength component of the control dependency edge. Specifically, the calculation method is to multiply the operating parameter adjustment amount in the master control command with the control strength component to obtain the parameter change amount that the downstream device node needs to respond to. At the same time, the execution time of the slave control command is determined according to the state switching timing requirements of the downstream device node. This execution time is set as the execution time of the master control command plus the response delay component to ensure the timing coordination of the control actions. In the same manner, control commands are generated sequentially for all downstream device nodes in the second, third and final levels. The control command for each downstream device node is calculated based on the control command of the device node in the previous level and the weight information of the corresponding control dependency edge.

[0128] After generating all control commands, constraint verification is performed on the main control command and each slave control command. The constraint verification process checks whether the adjustment amount of the operating parameters in each control command exceeds the allowable adjustment range of the corresponding device node. For the main control command, its operating parameter adjustment amount is compared with the root cause device node's own operating parameter adjustment range constraint; for each slave control command, its coordinated adjustment amount is compared with the operating parameter adjustment range constraint of the corresponding downstream device node. When it is detected that the adjustment amount of a control command exceeds the constraint range, the excess adjustment amount is reduced and corrected by reducing the adjustment amount to the allowable operating parameter adjustment range boundary value. The difference in adjustment amount after reduction needs to be redistributed to other device nodes in the influence domain topology subgraph to maintain the overall control effect. The target device node for redistribution is selected from device nodes at the same or adjacent topology levels as the current device node. The selection criteria are that the target device node still has remaining capacity in its operating parameter adjustment range constraint and its function is similar to that of the current device node. The reduced adjustment amount difference is distributed according to the proportion of the target device node's remaining capacity, and the slave control commands of the target device node are updated accordingly.

[0129] Simultaneously, the constraint verification process also checks whether the execution timing of each control command meets the state transition timing requirements. The verification method involves verifying whether the difference between the execution time of the slave control command of a subsequent-level device node and the execution time of the control command of a preceding-level device node is greater than or equal to the response delay component of the corresponding control dependency edge. When a timing violation is detected, the execution time of the slave control command of the subsequent-level device node is adjusted, delaying it to the earliest time that meets the response delay component requirement. After adjustment constraint verification and timing constraint verification, an optimized set of master control commands and optimized set of slave control commands that satisfy all control constraints is obtained.

[0130] In one optional implementation, the method further includes:

[0131] The feasibility of the operation parameter adjustment amounts in the main control command and the coordinated adjustment amounts in the secondary control command is verified by substituting them into the control constraints.

[0132] When the adjustment amount is detected to exceed the adjustment range of the operating parameters or violate the state switching timing requirements, the excessive adjustment amount is reduced and corrected and redistributed to other device nodes in the influence domain topology subgraph to obtain optimized master control instructions and optimized slave control instructions that satisfy the control constraints. The optimized master control instructions are then output as the priority processing instructions.

[0133] The feasibility verification also examines the state transition timing requirements. This verification focuses on the execution time of control commands to ensure that the control actions of each level of device node satisfy the timing sequence of control propagation. For each control dependency edge in the influence domain topology subgraph, which connects an upstream and downstream device node, its edge attributes include a response delay component. This response delay component defines the minimum time interval required for the downstream device node to begin responding after the upstream device node's control command takes effect. The execution time of the upstream device node's control command and the execution time of the downstream device node's control command are extracted, and the time difference between the two execution times is calculated. This time difference is compared with the response delay component of the corresponding control dependency edge. If the time difference is less than the response delay component, the control command is determined to violate the state transition timing requirements and is marked as a command requiring timing adjustment. By traversing all control dependency edges and their connected device node pairs in the influence domain topology subgraph, the set of all control commands that violate the state transition timing requirements is obtained.

[0134] For control commands that violate the operating parameter adjustment range constraints, a reduction correction operation is performed. For master control commands, when their operating parameter adjustment exceeds the upper limit of the operating parameter adjustment range of the root cause device node, the operating parameter adjustment is reduced to the upper limit. The reduction method is to directly set the value of the operating parameter adjustment to the upper limit while keeping the adjustment direction unchanged. The difference in operating parameter adjustment before and after reduction is calculated. This difference represents the adjustment that cannot be implemented on the root cause device node due to constraints, and is recorded as the adjustment to be allocated. For slave control commands, when their coordinated adjustment exceeds the upper limit of the operating parameter adjustment range of the corresponding downstream device node, the same reduction operation is performed, reducing the coordinated adjustment to the upper limit of the operating parameter adjustment range of the corresponding device node, and calculating the adjustment to be allocated resulting from the reduction. Through the reduction correction operation, it is ensured that the adjustment values ​​of all control commands do not exceed the operating parameter adjustment range constraints of the corresponding device nodes.

[0135] The adjustment amount to be allocated resulting from the reduction correction needs to be reallocated to other device nodes in the influence domain topology subgraph to maintain the equivalence of the overall control effect. The reallocation operation first determines a set of candidate device nodes that can receive the adjustment amount to be allocated. Candidate device nodes must meet two conditions: First, the candidate device node is at the same or adjacent topology level as the original device node that generated the adjustment amount to be allocated in the influence domain topology subgraph, to ensure the timing coordination of control actions; second, the current control command adjustment amount of the candidate device node has not yet reached its upper limit for adjusting operating parameters, meaning the candidate device node still has adjustment capacity to accept additional adjustments. By traversing all device nodes in the influence domain topology subgraph and checking the above two conditions, a set of candidate device nodes is obtained.

[0136] For each candidate device node in the candidate device node set, its remaining adjustment capacity is calculated. The remaining adjustment capacity equals the upper limit of the candidate device node's operating parameter adjustment range minus the absolute value of the current control command's adjustment amount. The remaining adjustment capacities of all candidate device nodes are summed to obtain the total remaining adjustment capacity. The allocation weight for each candidate device node is calculated, equal to its remaining adjustment capacity divided by the total remaining adjustment capacity. The allocation weight reflects the relative proportion of adjustment that the candidate device node can bear among all candidate device nodes. The adjustment amount to be allocated is proportionally distributed according to the allocation weights of each candidate device node. The specific allocation amount equals the adjustment amount to be allocated multiplied by the corresponding candidate device node's allocation weight. The allocated adjustment amount is then added to the control command of the corresponding candidate device node, updating the adjustment value of that candidate device node's control command. This redistribution mechanism ensures that the reduced adjustment amount is equivalently compensated within the influence domain, avoiding a decline in overall control effectiveness due to single-point constraints.

[0137] This invention provides a collaborative alarm processing system for computer room air conditioning systems designed for group control of equipment, comprising:

[0138] The first unit is used to acquire alarm information generated by multiple air conditioning devices in the computer room within the current time window, and to perform spatial correlation analysis on the alarm information based on the preset device topology relationship to obtain an alarm set with spatial coupling characteristics. The device topology relationship includes the supply air path dependency relationship and return air path dependency relationship between devices.

[0139] The second unit is used to map the alarm information to a pre-constructed device group control collaborative graph structure based on the device identifier in the alarm information and the spatial coupling feature. The device group control collaborative graph structure includes device nodes, alarm propagation edges, and control dependency edges between devices. The weight of the alarm propagation edge is determined by the airflow influence degree between devices and the alarm timing correlation degree.

[0140] The third unit is used to identify the root cause device node that causes the alarm set by using a reverse path tracing algorithm based on the device group control collaborative graph structure. Based on the root cause device node and its associated control dependency edge, it generates a priority processing instruction for the root cause device node. The priority processing instruction includes device control parameter adjustment actions and alarm suppression strategies. The priority processing instruction is then sent to the air conditioning equipment corresponding to the root cause device node.

[0141] A third aspect of the present invention provides an electronic device, comprising:

[0142] processor;

[0143] Memory used to store processor-executable instructions;

[0144] The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0145] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0146] This invention can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the invention.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A collaborative alarm processing method for computer room air conditioning for equipment group control, characterized in that, include: The alarm information generated by multiple air conditioning devices in the computer room within the current time window is obtained. Based on the preset device topology relationship, the spatial correlation analysis of the alarm information is performed to obtain an alarm set with spatial coupling characteristics. The device topology relationship includes the supply air path dependency relationship and return air path dependency relationship between devices. Based on the device identifier in the alarm information and the spatial coupling feature, the alarm information is mapped to a pre-constructed device group control collaborative graph structure. The device group control collaborative graph structure includes device nodes, alarm propagation edges, and control dependency edges between devices. The weight of the alarm propagation edge is determined by the airflow influence degree between devices and the alarm timing correlation degree. Based on the device group control collaborative graph structure, a reverse path tracing algorithm is used to identify the root cause device node that causes the alarm set. According to the root cause device node and its associated control dependency edge, a priority processing instruction for the root cause device node is generated. The priority processing instruction includes device control parameter adjustment actions and alarm suppression strategies. The priority processing instruction is then sent to the air conditioning equipment corresponding to the root cause device node. Based on the root cause device node and its associated control dependency edges, priority processing instructions are generated for the root cause device node, including: Starting from the root cause device node, a breadth-first traversal is performed along the positive direction of the control dependency edges in the device group control collaboration graph structure to identify all downstream device nodes directly or indirectly affected by the root cause device node, and to construct an influence domain topology subgraph containing the root cause device node and all downstream device nodes; For each downstream device node in the influence domain topology subgraph, the control constraint conditions corresponding to the downstream device node are extracted from the edge attributes of the control-dependent edge. The control constraints include the allowable adjustment range of the operating parameters of the downstream device node and the state switching timing requirements of the downstream device node. The adjustment range of the operating parameters is determined by the control strength component in the control dependency edge weights, and the state switching timing requirements are determined by the response delay component in the control dependency edge weights. Based on the topological hierarchy of the influence domain topology subgraph, and in accordance with the control transmission sequence from the root cause device node to the downstream device node, a master control command is generated for the root cause device node, and a slave control command is generated for each downstream device node. The feasibility of the operation parameter adjustment amounts in the main control command and the coordinated adjustment amounts in the secondary control command is verified by substituting them into the control constraints. When the adjustment amount is detected to exceed the adjustment range of the operating parameters or violate the state switching timing requirements, the excessive adjustment amount is reduced and corrected and redistributed to other device nodes in the influence domain topology subgraph to obtain optimized master control instructions and optimized slave control instructions that satisfy the control constraints. The optimized master control instructions are then output as the priority processing instructions.

2. The method according to claim 1, characterized in that, Based on a preset device topology, spatial correlation analysis is performed on the alarm information to obtain an alarm set with spatial coupling characteristics, including: Based on the device identifier in the alarm information, the spatial location coordinates and airflow direction vector of the device corresponding to each alarm information are extracted from the device topology relationship. Combined with the alarm timestamp, the alarm timing difference between adjacent devices is calculated to obtain an alarm spatiotemporal feature matrix that includes spatial distance features and timing interval features. Based on the supply air path dependency and the return air path dependency, airflow conduction path matching is performed on each alarm information in the alarm spatiotemporal feature matrix, and the spatial coupling degree between devices on the same airflow conduction path is calculated. The spatial coupling degree is determined by the connectivity of the airflow conduction path and the spatial distance feature. Alarm information whose spatial coupling exceeds a preset coupling threshold is grouped into the same alarm set to obtain the alarm set with spatial coupling characteristics.

3. The method according to claim 2, characterized in that, Based on the supply air path dependency and the return air path dependency, airflow conduction path matching is performed on each alarm information in the alarm spatiotemporal feature matrix, and the spatial coupling degree between devices on the same airflow conduction path is calculated, including: Based on the supply air path dependency and the return air path dependency, a directed graph of airflow conduction paths is constructed. The nodes of the directed graph of airflow conduction paths correspond to the device identifiers in the alarm spatiotemporal feature matrix. The directed edges of the directed graph of airflow conduction paths represent the airflow conduction relationship in the supply air direction or the return air direction. The edge weight of the directed edge is determined by the consistency degree of the airflow direction vector and the reciprocal of the spatial distance feature. For each pair of alarm messages, a connectivity test is performed on the directed graph of the airflow conduction path to determine whether a directed connected path exists between the device nodes corresponding to the two alarm messages; If it exists, the cumulative attenuation calculation is performed on the edge weights of all directed edges on the directed connected path to obtain the spatial coupling degree of the device node pair. The cumulative attenuation calculation is achieved by weighted summation of the edge weights of each directed edge on the path and applying a path length attenuation factor. The path length attenuation factor decreases as the number of nodes contained in the directed connected path increases.

4. The method according to claim 1, characterized in that, Based on the device group control collaborative graph structure, the root cause device node leading to the alarm set is identified using a reverse path tracing algorithm, including: Traverse all device nodes in the device group control collaboration graph structure, and based on the alarm information in the alarm set, mark the device nodes that generate alarms as alarm nodes and assign them an initial alarm propagation contribution, and mark the device nodes that do not generate alarms as candidate root cause nodes; The system iterates along the reverse direction of the control dependency edges in the device group control collaboration graph structure. For each alarm node, it identifies the upstream device node that is pointed to by the control dependency edge, and propagates the alarm propagation contribution of the alarm node to the upstream device node in reverse according to the weight of the alarm propagation edge. The reverse propagation is achieved by combining the alarm propagation contribution with the attenuation coefficient of the alarm propagation edge weight, so as to obtain the cumulative alarm propagation contribution of each upstream device node. During the iterative traversal, only propagation paths that satisfy the control dependency edge directionality constraint are retained. The directionality constraint requires that the direction of the control dependency edge on the propagation path be consistent with the causal direction of alarm propagation. When the iterative traversal terminates, the device node with the largest cumulative alarm propagation contribution is selected from the candidate root cause nodes as the root cause device node.

5. The method according to claim 4, characterized in that, Based on the weight of the alarm propagation edge, the alarm propagation contribution of the alarm node is propagated back to the upstream device node, including: The weights of the alarm propagation edge are decomposed into an airflow influence component and an alarm timing correlation component. The airflow influence component represents the intensity of the airflow transmission influence of the upstream device node on the alarm node, and the alarm timing correlation component represents the temporal correlation strength between the change in the operating state of the upstream device node and the alarm occurrence time of the alarm node. For each incident alarm propagation edge of an alarm node, a nonlinear fusion calculation is performed on the airflow influence component and the alarm timing correlation component to obtain the comprehensive transmission coefficient of the incident alarm propagation edge. The nonlinear fusion calculation is achieved by multiplying the airflow influence component and the alarm timing correlation component and applying normalization processing. The alarm propagation contribution of the alarm node is multiplied by the comprehensive transmission coefficient to obtain the contribution increment transmitted to the corresponding upstream device node through the incident alarm propagation edge; The contribution increment is added to the current cumulative alarm propagation contribution of the corresponding upstream device node to complete the update of the cumulative alarm propagation contribution of the upstream device node.

6. A collaborative processing system for alarms in computer room air conditioning systems for equipment group control, used to implement the method as described in any one of claims 1-5, characterized in that, include: The first unit is used to acquire alarm information generated by multiple air conditioning devices in the computer room within the current time window, and to perform spatial correlation analysis on the alarm information based on the preset device topology relationship to obtain an alarm set with spatial coupling characteristics. The device topology relationship includes the supply air path dependency relationship and return air path dependency relationship between devices. The second unit is used to map the alarm information to a pre-constructed device group control collaborative graph structure based on the device identifier in the alarm information and the spatial coupling feature. The device group control collaborative graph structure includes device nodes, alarm propagation edges, and control dependency edges between devices. The weight of the alarm propagation edge is determined by the airflow influence degree between devices and the alarm timing correlation degree. The third unit is used to identify the root cause device node that causes the alarm set by using a reverse path tracing algorithm based on the device group control collaborative graph structure. Based on the root cause device node and its associated control dependency edge, it generates a priority processing instruction for the root cause device node. The priority processing instruction includes device control parameter adjustment actions and alarm suppression strategies. The priority processing instruction is then sent to the air conditioning equipment corresponding to the root cause device node.

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 5.

Images