BIM software automated full life cycle management method for virtualized resource pool

Abstract

The present invention discloses a BIM software automation full life cycle management method for a virtualized resource pool, S1, initiates a BIM resource application through a user self-service page; S2, after receiving the application, the desktop cloud resource scheduler checks whether the physical resources meet the demand; S3, when the resources meet the demand, a virtual machine instance is created based on the computing power demand and the BIM software is deployed; S4, when the resources are insufficient, a dynamic association adaptive resource coordination algorithm is used to adjust the resource configuration between tasks; S5, a computing power resource hierarchical reuse algorithm driven by time-varying feedback is used to dynamically adjust resource allocation; S6, monitors virtual machine instances, recycles resources that are no longer used and reallocates them; S7, performs resource scheduling through a computing power resource time-sharing reuse strategy. The present invention improves resource utilization and is suitable for complex BIM application scenarios.

Description

Technical Field

[0001] The present invention relates to the field of virtualization technology, and in particular to a BIM software automated full life cycle management method for a virtualized resource pool. Background Art

[0002] In the current Building Information Modeling (BIM) management process, with the widespread adoption of BIM technology and the continuous expansion of project scale, efficient resource management and scheduling has become a major challenge. BIM software is used in the entire lifecycle management of buildings, including design, construction, and maintenance. With the increasing demand for multi-tasking and parallel processing, the shortcomings of existing technologies in resource management are becoming increasingly apparent. Current BIM resource management technologies mostly rely on static configurations, and resource scheduling is relatively fixed. This approach is sufficient for small-scale projects or when resources are sufficient, but in complex, multi-tasking construction projects, it exposes serious problems such as inefficient resource utilization and slow scheduling response.

[0003] In existing BIM management systems, resource allocation and scheduling largely rely on pre-set algorithms or human intervention, lacking flexibility. This makes it difficult for the system to respond quickly, especially when resource demand fluctuates significantly. For example, when the resource demand for certain tasks decreases, the system is unable to promptly release occupied resources, resulting in resource waste. Furthermore, in situations of resource shortage, the system is unable to effectively allocate temporarily idle resources to other tasks through dynamic scheduling. This results in not only long periods of idle resources in the resource pool, but also delays or interruptions to certain tasks due to insufficient resources, severely impacting the overall progress and efficiency of the project.

[0004] More critically, existing BIM management technologies' resource scheduling methods are too rigid, unable to adapt in real time to changing requirements during task execution. Even with the introduction of dynamic adjustment mechanisms in scheduling algorithms, their adaptability remains limited. As projects expand in scale and complexity, resource requirements vary significantly between tasks, and resource usage by different tasks also fluctuates over time. This makes static resource allocation strategies ineffective in complex scenarios. Low resource utilization and delayed scheduling ultimately lead to decreased project execution efficiency.

[0005] At the same time, resource contention in existing systems is particularly prominent when processing concurrent tasks. When multiple tasks simultaneously request the same resource, the system struggles to coordinate effectively, leading to increased resource contention. This not only prevents some tasks from executing smoothly due to insufficient resource support, but also further prolongs the overall project completion time. Furthermore, in some cases, despite changes in task resource requirements, the system lacks a dynamic mechanism for adjusting task priorities. This means that low-priority tasks may occupy a significant portion of resources, while high-priority tasks remain stagnant due to insufficient resources.

[0006] In addition to the problems of low resource utilization and insufficient scheduling efficiency, existing BIM management systems also have defects in their resource reuse mechanisms. When certain tasks are completed, the system is often unable to promptly reclaim the released resources and allocate them to new tasks. Especially in situations of resource constraints, this lag in resource recovery and reuse will result in the resources in the resource pool not being used to their maximum efficiency. The current scheduling mechanism lacks intelligent resource control means and is unable to effectively recycle and redistribute resources according to real-time needs, which seriously affects the overall resource management efficiency of the system. Therefore, how to provide an automated full-lifecycle management method for BIM software for virtualized resource pools is an urgent problem that those skilled in the art need to solve. Summary of the Invention

[0007] One objective of the present invention is to propose an automated full-lifecycle management method for BIM software in a virtualized resource pool, enabling efficient application, scheduling, allocation, and recycling of BIM resources. This method leverages virtualized resource scheduling technology, optimizes resource utilization through intelligent algorithms, ensures efficient resource allocation, and adapts to complex multi-tasking parallel processing environments, offering advantages such as high flexibility, high resource utilization, and fast system response.

[0008] The BIM software automated full lifecycle management method for a virtualized resource pool according to an embodiment of the present invention includes the following steps:

[0009] S1. Through the user self-service page, the user initiates an application for BIM resources through the WEB interface;

[0010] S2. After receiving the BIM environment resource application request, the desktop cloud resource scheduler checks whether the physical resources in the cloud desktop resource pool meet the requirements;

[0011] S3. When the resources in the resource pool meet the demand, a virtual machine instance is automatically created based on the computing power requirements of the BIM software application, and the BIM software is deployed to the virtual machine instance to complete resource delivery;

[0012] S4. When the resources in the resource pool cannot meet the demand, a dynamic association adaptive resource coordination algorithm is used to identify and adjust the resource allocation between different tasks and coordinate resources between tasks;

[0013] S5. When resource coordination still cannot meet the demand, BIM resource applications are added to the task queue, and a time-varying feedback-driven computing resource layered reuse algorithm is used to dynamically adjust computing resource allocation based on feedback information during task execution.

[0014] S6. Monitor the usage status of virtual machine instances, reclaim unused BIM environment resources, and reallocate the reclaimed resources to new task requests;

[0015] S7. Through the strategy of time-sharing reuse of computing resources, integrate the computing resources in the resource pool, allocate resources and perform scheduling.

[0016] Optionally, S3 includes the following steps:

[0017] S31. When the desktop cloud resource scheduler confirms that the physical resources in the resource pool meet the user's application requirements, Determine the computing power parameters required for the virtual machine instance, including CPU requirements Memory requirements , storage requirements and network bandwidth requirements ;

[0018] S32: The desktop cloud resource scheduler calls the resource pool in the virtualization platform according to the computing power demand parameters to create a virtual machine instance. ,in Indicates the virtual machine instances;

[0019] S33, virtual machine instance After successful creation, the required BIM software Deploy to the instance. The deployment process includes software installation, configuration, and importing related dependency files.

[0020] S34. After the BIM software is deployed, the resource information of the virtual machine instance, the BIM software application information and the allocation status are recorded in the database. The record includes The unique identifier of the task, the number of resources allocated, and the task number ;

[0021] S35, generate feedback information, and send the virtual machine instance Deliver relevant information to users;

[0022] S36. Dynamically monitor the virtualized resource pool during virtual machine instance deployment.

[0023] S37. If resource conflicts or errors occur during virtual machine instance creation or BIM software deployment, record the error log and try to reschedule resources for repair or redeployment.

[0024] Optionally, the S4 includes the following steps:

[0025] S41. When the physical resources in the resource pool cannot meet the demand, the desktop cloud resource scheduler calls the dynamic association adaptive resource coordination algorithm; for each task Build time-dependent resource requirement vector: ;in, For the task In time The number of CPU cores required; For the task In time The amount of memory required; For the task In time The amount of storage required; For the task In time Required network bandwidth;

[0026] S42. Introducing the dynamic correlation matrix , combined with the changing trend of task historical requirements; used to measure task and tasks The resource demand correlation between:

[0027] ;

[0028] Among them, the first measurement task and tasks The similarity of resource requirements at each moment captures the current resource requirements; the second measurement task and tasks The resource demand change trend is captured by time derivatives to capture the dynamic changes of history; Used to control the impact of historical demand change trends on relevance;

[0029] S43. Calculate the dynamic priority coefficient for each task based on the dynamic relevance of the task , used to determine the priority of tasks in resource allocation; the calculation formula of the priority coefficient is:

[0030] ;

[0031] in, For the task In time priority; Task and tasks Dynamic correlation of

[0032] S44, introduce task adaptive adjustment coefficient , which is used to make real-time adjustments based on the actual resource usage and expected demand of the task. The adjustment formula is:

[0033] ;

[0034] in, For the task Adaptive adjustment coefficient; To adjust the difference between actual use and expected use; For the task In time Actual resource usage; For the task the expected resource requirements; To control the correlation between tasks Impact on adaptive regulation;

[0035] S45. According to the priority coefficient of the task and adaptive adjustment coefficient , dynamically calculate the resource allocation for each task ;

[0036] S46. To optimize resource allocation, a spatiotemporal feedback control mechanism is introduced to adjust the resource allocation of tasks through real-time feedback;

[0037] S47. Based on the execution of tasks, the spatiotemporal feedback control mechanism is used to continuously optimize resource allocation.

[0038] Optionally, the S5 includes the following steps:

[0039] S51. When resource coordination still cannot meet the demand, BIM resources apply to join the task queue; build a hierarchical computing model based on the different resource requirements of the task; each task The computing power demand vector is decomposed into ;in, For the task In time CPU computing power requirements; For the task In time Memory computing power requirements; For the task In time Storage and computing power requirements; For the task In time Network computing power requirements; For the task In time The energy demand, which represents the energy consumed by the task;

[0040] S52. Introduce a high-dimensional time-varying feedback driven model to dynamically adjust the hierarchical computing power requirements of tasks based on real-time feedback information; define the time-varying feedback coefficient matrix , which is used to regulate the dynamic changes of hierarchical requirements of tasks over time, is derived as follows:

[0041] ;

[0042] in, is the identity matrix, keeping the original demand unchanged; is the feedback adjustment coefficient, which controls the intensity of the feedback impact; is the feedback frequency, which indicates the periodicity of feedback fluctuation; is the phase offset, indicating the task Feedback response delay; is the nonlinear feedback attenuation coefficient, which is used to control the impact of resource demand fluctuation on feedback;

[0043] S53, according to the time-varying feedback coefficient matrix , dynamically adjust the hierarchical computing power requirements of tasks;

[0044] S54, further optimize the resource allocation of tasks through the dynamic collaborative layering model; collaborative layering matrix Indicates a task and tasks The synergistic effect of computing power resource stratification is derived as follows:

[0045] ;

[0046] in, is the eigenvalue of the synergy matrix, indicating that The strength of collaboration on the layer; the first item represents the task and tasks The synergistic effect of computing power requirements changing over time; the second one controls the resource requirements differences between different tasks through nonlinear decay; To control the impact of differences in resource requirements on synergy;

[0047] S55. Adjust requirements based on task feedback and collaborative layering matrix , calculate the final resource allocation , the allocation formula is:

[0048] ;

[0049] in, For the task The final resource allocation obtained; It is a collaborative hierarchical matrix used to adjust the collaboration and resource requirements between tasks;

[0050] S56. To further optimize resource utilization, a nonlinear spatiotemporal feedback control mechanism is introduced to dynamically regulate resource allocation by combining temporal and spatial feedback. The derived formula is as follows:

[0051] ;

[0052] in, is the spatiotemporal feedback adjustment coefficient, which controls the impact of spatiotemporal feedback on resource allocation; is the spatial control function, which reflects the resource requirements of the task in the spatial location; is the spatial position attenuation coefficient, which is used to control the resource distribution of tasks in different spatial positions; is the initial spatial position of the task;

[0053] S57. Through the spatiotemporal feedback control mechanism, the resource allocation of tasks is dynamically monitored and adjusted, so that tasks can achieve efficient resource layering reuse and regulation when the resource pool is limited.

[0054] Optionally, the S6 includes the following steps:

[0055] S61, monitor the usage status of virtual machine instances and collect resource usage data of each virtual machine instance, defined as , which includes CPU usage , memory usage , storage usage and network bandwidth usage ;

[0056] S62. By evaluating the resource usage data of the virtual machine instance , computing resource utilization , and analyze whether the resources in the virtual machine instance are fully utilized;

[0057] S63, when the resource utilization of the virtual machine instance Below the preset threshold for a long time When the resource of the virtual machine instance enters the recycling state, it is determined whether the resource of the virtual machine instance enters the recycling state;

[0058] S64: For virtual machine instances that meet the recycling conditions, unused resources are recycled from the instances through the resource recycling mechanism to generate a recycled resource vector. , representing a virtual machine instance The amount of recycled resources in

[0059] S65. Recycled resources The resource pool is re-added and resources are dynamically allocated based on the new task requirements. The allocation is based on the task priority and the resource requirements of the current task, and the amount of resources reallocated to the new task. ; Allocate based on available resources in the resource pool;

[0060] S66. After the resources are reallocated, monitor the resource usage of the new task in real time, and collect and analyze the resource usage data of the new task instance;

[0061] S67. Further optimize and dynamically adjust resource allocation between tasks based on the resource usage status of the new task.

[0062] Optionally, the S7 includes the following steps:

[0063] S71, real-time collection task Resource requirements, building a task-resource bidirectional response matrix , used to capture tasks Resources The time-varying effect of is defined as follows:

[0064] ;

[0065] in, For the task In time resource requirements; For the task In time The rate of change of resource demand; For resources The time-varying response function is used to represent the resource Task the responsiveness of demand, based on the current availability of resources; Indicates the change from the initial time to the current time;

[0066] S72, Resources The time-varying response function It represents the dynamic response of resources to changes in task requirements, taking into account resource availability and load fluctuations. The derived formula is:

[0067] ;

[0068] in, For resources In time The actual amount of resources available; For resources In time Maximum available capacity; For resources The minimum resource limit indicates the minimum resource usage limit; To regulate the attenuation coefficient, we control the decay rate of resource response changes. A larger value indicates that the resource is more sensitive to changes.

[0069] S73, based on the two-way response of tasks and resources, using nonlinear resource control function Dynamically adjust resource allocation between tasks; resource allocation priority Defined as:

[0070] ;

[0071] in, It is a two-way response matrix of tasks and resources, reflecting the task Resources the impact of; Current time Total available resources in the resource pool; For the task Resource requirements at the current time; A small constant used to avoid the denominator being zero;

[0072] S74. During the resource allocation process, the actual usage of tasks is dynamically adjusted through the feedback control mechanism; the feedback control function Adjust based on the difference between actual usage of tasks and expected demand;

[0073] S75. Final resource allocation for the task Comprehensive feedback control function and nonlinear resource regulation functions , defined as: ;

[0074] S76. Continuously adjust resource allocation priorities based on real-time feedback to ensure that tasks receive adequate resource support in a timely manner as resource requirements change. Real-time adjustments are determined by task feedback and resource pool availability.

[0075] S77. Analyze the execution feedback of the task and further optimize the time-sharing reuse strategy of computing resources.

[0076] The beneficial effects of the present invention are:

[0077] This invention introduces a dynamic, adaptive resource coordination algorithm to dynamically adjust resources between tasks when resources are insufficient. By intelligently analyzing the correlation between resource requirements between tasks, the system can effectively coordinate resource allocation across different tasks, avoiding the task delays and resource waste caused by insufficient resources in traditional methods. This significantly improves the efficiency of system resource utilization and the smoothness of task execution.

[0078] This invention uses a time-varying feedback-driven layered computing resource reuse algorithm, dynamically adjusting resource allocation strategies based on feedback during task execution. The system can capture changes in resource requirements during task execution in real time and optimize resource allocation through feedback mechanisms, ensuring flexible and efficient reuse of resources within the resource pool.

[0079] This mechanism not only improves the system's resource management capabilities, but also effectively reduces delays and efficiency losses caused by resource mismatches during task execution. It is particularly suitable for complex multi-tasking parallel BIM environments.

[0080] This invention incorporates a resource monitoring and recovery mechanism that, by monitoring the usage status of virtual machine instances in real time, promptly recovers resources from completed or underutilized tasks and reallocates them to new tasks. Unlike traditional systems, which struggle with timely resource recovery and allocation, this mechanism ensures that resources in the resource pool remain efficiently utilized, reducing idle resource time and further improving system responsiveness and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0082] Figure 1 This is an overall flow chart of the BIM software automated full life cycle management method for virtualized resource pools proposed by the present invention;

[0083] Figure 2 Schematic diagram of the present invention using a dynamic association adaptive resource coordination algorithm to adjust resources between tasks when resources are insufficient;

[0084] Figure 3 This is a schematic diagram of the present invention using a time-varying feedback-driven computing resource layered reuse algorithm for resource allocation and reuse. DETAILED DESCRIPTION

[0085] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0086] refer to Figure 1-3 , a BIM software automated full life cycle management method for a virtualized resource pool includes the following steps:

[0087] S1. Through the user self-service page, the user initiates an application for BIM resources through the WEB interface;

[0088] S2. After receiving the BIM environment resource application request, the desktop cloud resource scheduler checks whether the physical resources in the cloud desktop resource pool meet the requirements;

[0089] S3. When the resources in the resource pool meet the demand, a virtual machine instance is automatically created based on the computing power requirements of the BIM software application, and the BIM software is deployed to the virtual machine instance to complete resource delivery;

[0090] S4. When the resources in the resource pool cannot meet the demand, a dynamic association adaptive resource coordination algorithm is used to identify and adjust the resource allocation between different tasks and coordinate resources between tasks;

[0091] S5. When resource coordination still cannot meet the demand, BIM resource applications are added to the task queue, and a time-varying feedback-driven computing resource layered reuse algorithm is used to dynamically adjust computing resource allocation based on feedback information during task execution.

[0092] S6. Monitor the usage status of virtual machine instances, reclaim unused BIM environment resources, and reallocate the reclaimed resources to new task requests;

[0093] S7. Through the strategy of time-sharing reuse of computing resources, integrate the computing resources in the resource pool, allocate resources and perform scheduling.

[0094] In this embodiment, S3 includes the following steps:

[0095] S31. When the desktop cloud resource scheduler confirms that the physical resources in the resource pool meet the user's application requirements, Determine the computing power parameters required for the virtual machine instance, including CPU requirements Memory requirements , storage requirements and network bandwidth requirements ;

[0096] S32: The desktop cloud resource scheduler calls the resource pool in the virtualization platform according to the computing power demand parameters to create a virtual machine instance. ,in Indicates the virtual machine instances;

[0097] S33, virtual machine instance After successful creation, the required BIM software Deploy to the instance. The deployment process includes software installation, configuration, and importing related dependency files.

[0098] S34. After the BIM software is deployed, the resource information of the virtual machine instance, the BIM software application information and the allocation status are recorded in the database. The record includes The unique identifier of the task, the number of resources allocated, and the task number ;

[0099] S35, generate feedback information, and send the virtual machine instance Deliver relevant information to users;

[0100] S36. Dynamically monitor the virtualized resource pool during virtual machine instance deployment.

[0101] S37. If resource conflicts or errors occur during virtual machine instance creation or BIM software deployment, record the error log and try to reschedule resources for repair or redeployment.

[0102] In this embodiment, S4 includes the following steps:

[0103] S41. When the physical resources in the resource pool cannot meet the demand, the desktop cloud resource scheduler calls the dynamic association adaptive resource coordination algorithm; for each task Build time-dependent resource requirement vector: ;in, For the task In time The number of CPU cores required; For the task In time The amount of memory required; For the task In time The amount of storage required; For the task In time Required network bandwidth;

[0104] S42. Introducing the dynamic correlation matrix , combined with the changing trend of task historical requirements; used to measure task and tasks The resource demand correlation between:

[0105] ;

[0106] Among them, the first measurement task and tasks The similarity of resource requirements at each moment captures the current resource requirements; the second measurement task and tasks The resource demand change trend is captured by time derivatives to capture the dynamic changes of history; Used to control the impact of historical demand change trends on relevance;

[0107] S43. Calculate the dynamic priority coefficient for each task based on the dynamic relevance of the task , used to determine the priority of tasks in resource allocation; the calculation formula of the priority coefficient is:

[0108] ;

[0109] in, For the task In time priority; Task and tasks Dynamic correlation of

[0110] S44, introduce task adaptive adjustment coefficient , which is used to make real-time adjustments based on the actual resource usage and expected demand of the task. The adjustment formula is:

[0111] ;

[0112] in, For the task Adaptive adjustment coefficient; To adjust the difference between actual use and expected use; For the task In time Actual resource usage; For the task the expected resource requirements; To control the correlation between tasks Impact on adaptive regulation;

[0113] S45. According to the priority coefficient of the task and adaptive adjustment coefficient , dynamically calculate the resource allocation for each task ;

[0114] S46. To optimize resource allocation, a spatiotemporal feedback control mechanism is introduced to adjust the resource allocation of tasks through real-time feedback;

[0115] S47. Based on the execution of tasks, the spatiotemporal feedback control mechanism is used to continuously optimize resource allocation.

[0116] In this embodiment, S5 includes the following steps:

[0117] S51. When resource coordination still cannot meet the demand, BIM resources apply to join the task queue; build a hierarchical computing model based on the different resource requirements of the task; each task The computing power demand vector is decomposed into ;in, For the task In time CPU computing power requirements; For the task In time Memory computing power requirements; For the task In time Storage and computing power requirements; For the task In time Network computing power requirements; For the task In time The energy demand, which represents the energy consumed by the task;

[0118] S52. Introduce a high-dimensional time-varying feedback driven model to dynamically adjust the hierarchical computing power requirements of tasks based on real-time feedback information; define the time-varying feedback coefficient matrix , which is used to regulate the dynamic changes of hierarchical requirements of tasks over time, is derived as follows:

[0119] ;

[0120] in, is the identity matrix, keeping the original demand unchanged; is the feedback adjustment coefficient, which controls the intensity of the feedback impact; is the feedback frequency, which indicates the periodicity of feedback fluctuation; is the phase offset, indicating the task Feedback response delay; is the nonlinear feedback attenuation coefficient, which is used to control the impact of resource demand fluctuation on feedback;

[0121] S53, according to the time-varying feedback coefficient matrix , dynamically adjust the hierarchical computing power requirements of tasks;

[0122] S54, further optimize the resource allocation of tasks through the dynamic collaborative layering model; collaborative layering matrix Indicates a task and tasks The synergistic effect of computing power resource stratification is derived as follows:

[0123] ;

[0124] in, is the eigenvalue of the synergy matrix, indicating that The strength of collaboration on the layer; the first item represents the task and tasks The synergistic effect of computing power requirements changing over time; the second one controls the resource requirements differences between different tasks through nonlinear decay; To control the impact of differences in resource requirements on synergy;

[0125] S55. Adjust requirements based on task feedback and collaborative layering matrix , calculate the final resource allocation , the allocation formula is:

[0126] ;

[0127] in, For the task The final resource allocation obtained; It is a collaborative hierarchical matrix used to adjust the collaboration and resource requirements between tasks;

[0128] S56. To further optimize resource utilization, a nonlinear spatiotemporal feedback control mechanism is introduced to dynamically regulate resource allocation by combining temporal and spatial feedback. The derived formula is as follows:

[0129] ;

[0130] in, is the spatiotemporal feedback adjustment coefficient, which controls the impact of spatiotemporal feedback on resource allocation; is the spatial control function, which reflects the resource requirements of the task in the spatial location; is the spatial position attenuation coefficient, which is used to control the resource distribution of tasks in different spatial positions; is the initial spatial position of the task;

[0131] S57. Through the spatiotemporal feedback control mechanism, the resource allocation of tasks is dynamically monitored and adjusted, so that tasks can achieve efficient resource layering reuse and regulation when the resource pool is limited.

[0132] In this embodiment, S6 includes the following steps:

[0133] S61, monitor the usage status of virtual machine instances and collect resource usage data of each virtual machine instance, defined as , which includes CPU usage , memory usage , storage usage and network bandwidth usage ;

[0134] S62. By evaluating the resource usage data of the virtual machine instance , computing resource utilization , and analyze whether the resources in the virtual machine instance are fully utilized;

[0135] S63, when the resource utilization of the virtual machine instance Below the preset threshold for a long time When the resource of the virtual machine instance enters the recycling state, it is determined whether the resource of the virtual machine instance enters the recycling state;

[0136] S64: For virtual machine instances that meet the recycling conditions, unused resources are recycled from the instances through the resource recycling mechanism to generate a recycled resource vector. , representing a virtual machine instance The amount of recycled resources in

[0137] S65. Recycled resources The resource pool is re-added and resources are dynamically allocated based on the new task requirements. The allocation is based on the task priority and the resource requirements of the current task, and the amount of resources reallocated to the new task. ; Allocate based on available resources in the resource pool;

[0138] S66. After the resources are reallocated, monitor the resource usage of the new task in real time, and collect and analyze the resource usage data of the new task instance;

[0139] S67. Further optimize and dynamically adjust resource allocation between tasks based on the resource usage status of the new task.

[0140] In this embodiment, S7 includes the following steps:

[0141] S71, real-time collection task Resource requirements, building a task-resource bidirectional response matrix , used to capture tasks Resources The time-varying effect of is defined as follows:

[0142] ;

[0143] in, For the task In time resource requirements; For the task In time The rate of change of resource demand; For resources The time-varying response function is used to represent the resource Task the responsiveness of demand, based on the current availability of resources; Indicates the change from the initial time to the current time;

[0144] S72, Resources The time-varying response function It represents the dynamic response of resources to changes in task requirements, taking into account resource availability and load fluctuations. The derived formula is:

[0145] ;

[0146] in, For resources In time The actual amount of resources available; For resources In time Maximum available capacity; For resources Minimum resource limits; To regulate the attenuation coefficient, we control the decay rate of resource response changes. A larger value indicates that the resource is more sensitive to changes.

[0147] S73, based on the two-way response of tasks and resources, using nonlinear resource control function Dynamically adjust resource allocation between tasks; resource allocation priority Defined as:

[0148] ;

[0149] in, It is a two-way response matrix of tasks and resources, reflecting the task Resources the impact of; Current time Total available resources in the resource pool; For the task Resource requirements at the current time; A small constant used to avoid the denominator being zero;

[0150] S74. During the resource allocation process, the actual usage of tasks is dynamically adjusted through the feedback control mechanism; the feedback control function Adjust based on the difference between actual usage of tasks and expected demand;

[0151] S75. Final resource allocation for the task Comprehensive feedback control function and nonlinear resource regulation functions , defined as: ;

[0152] S76. Continuously adjust resource allocation priorities based on real-time feedback to ensure that tasks receive adequate resource support in a timely manner as resource requirements change. Real-time adjustments are determined by task feedback and resource pool availability.

[0153] S77. Analyze the execution feedback of the task and further optimize the time-sharing reuse strategy of computing resources.

[0154] Example 1:

[0155] In modern transportation planning projects, with the rapid development of cities and the increasing complexity of transportation demands, transportation planning and management systems need to process massive amounts of traffic data and perform multi-task planning and scheduling in parallel. For example, multiple tasks such as urban road design, traffic flow forecasting, and public transportation route optimization often need to be performed simultaneously, and the computing resource requirements of each task also vary over time. Due to the static nature of resource scheduling, traditional transportation planning systems often cannot flexibly adjust resource allocation based on real-time task demands, resulting in problems such as low resource utilization and task delays.

[0156] In this embodiment, the present invention is applied to a transportation planning project for a large city. The core task of this project is to simultaneously carry out multiple transportation planning sub-projects, including new road design, traffic flow forecasting, public transportation network optimization, and other concurrent tasks. These tasks require data analysis and model simulation using BIM software in a virtualized environment, requiring the system to have highly flexible resource scheduling capabilities.

[0157] In this scenario, traditional traffic planning systems struggle to cope with complex and changing resource demands. Taking new road design and traffic flow forecasting as an example, in the initial stages, the new road design task requires a greater amount of computing power, while the traffic flow forecasting task requires less computing power due to the data collection and preprocessing phases. However, as the new road design task is gradually completed, its computing power requirements gradually decrease, while the traffic flow forecasting task's resource requirements surge when it enters the model simulation and data analysis phases. If relying on traditional static resource scheduling methods, the system will find it difficult to flexibly adjust resources based on task changes. This may cause some tasks to be delayed due to insufficient resources, while resource-intensive tasks will become idle.

[0158] To solve this problem, the virtualized resource pool management method proposed in the present invention automatically schedules resources when resources are tight and optimizes resource allocation between tasks through a dynamic association adaptive resource coordination algorithm and a time-varying feedback-driven computing power resource hierarchical reuse algorithm. At the beginning of the project, the system first initiates a resource application for the traffic planning task through the user self-service page, and the scheduler checks the current resource pool. If the resources in the resource pool meet the demand, the system will automatically create virtual machine instances based on the computing power demand and assign them to each task to ensure the parallel execution of the tasks. When the new road design task reaches the mid-term stage, the resource demand decreases, and the system automatically adjusts the resources dynamically through a time-varying feedback-driven algorithm, allocating some idle resources to the traffic prediction task, avoiding waste of resources. At the same time, the computing power demand of the traffic prediction task gradually increases with the increase in data simulation workload, and the system monitors feedback in real time to ensure that the resources required for the task can be allocated in the shortest time.

[0159] The data proves the superiority of this invention in this traffic planning project. In the first month of the project, the system recorded the resource allocation of different tasks. The resource allocation of the new road design task from the 1st to the 5th day accounted for as much as 70%, while the allocated resources for the traffic flow forecasting task were only 30%. As the resource requirements of the design task gradually decreased, the system dynamically allocated these idle resources to the traffic flow forecasting task. By the 15th day, the resource allocation ratio of the traffic flow forecasting task increased to 65%, while that of the new road design task decreased to 35%. This flexible scheduling of resources greatly improved the overall resource utilization of the system.

[0160] Especially at key project milestones, traffic planning simulation tasks required significant resources. The system's adaptive resource allocation mechanism ensured that traffic flow prediction tasks received 90% of available resources, while other lower-priority tasks were allocated resources through a dynamically linked adaptive resource coordination algorithm. By day 30, the project's resource utilization rate reached 95%, a 25% improvement over the average utilization rate of traditional static scheduling systems.

[0161] Furthermore, project execution time was significantly reduced. Data analysis revealed that, under traditional scheduling methods, the project was expected to take 60 days to complete. However, using the resource scheduling method presented in this paper, the actual execution time was reduced to 52 days. This system not only improved resource utilization but also effectively shortened the overall project timeline, saving significant costs and human resources.

[0162] Table 1 Data table

[0163]

[0164] The data table shows the resource scheduling effect of the present invention in actual application, proving the outstanding performance of the present invention in optimizing resource utilization, shortening scheduling response time, and improving task execution efficiency.

[0165] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A BIM software automated full life cycle management method for a virtualized resource pool, characterized in that: The steps include: S1. Through the user self-service page, the user initiates an application for BIM resources through the WEB interface; S2. After receiving the BIM environment resource application request, the desktop cloud resource scheduler checks whether the physical resources in the cloud desktop resource pool meet the demand; S3. When the resources in the resource pool meet the demand, a virtual machine instance is automatically created based on the computing power demand of the BIM software application, and the BIM software is deployed on the virtual machine instance to complete resource delivery; S4. When the resources in the resource pool cannot meet the demand, a dynamic associated adaptive resource coordination algorithm is used to identify and adjust the resource allocation between different tasks and coordinate resources between tasks; S5. When resource coordination still cannot meet the demand, the BIM resource application is added to the task queue, and the computing resource layered reuse algorithm driven by time-varying feedback is adopted to dynamically adjust the computing resource allocation based on the feedback information during the task execution process; S6. Monitor the usage status of virtual machine instances, recycle unused BIM environment resources, and reallocate the reclaimed resources to new task requests; S7. Through the strategy of time-sharing reuse of computing resources, integrate the computing resources in the resource pool, allocate resources and perform scheduling.

2. The BIM software automated full life cycle management method for a virtualized resource pool according to claim 1, characterized in that: The S3 comprises the following steps: S31. When the desktop cloud resource scheduler confirms that the physical resources in the resource pool meet the user's application requirements, according to the BIM software application type Determine the computing power parameters required for the virtual machine instance, including CPU requirements Memory requirements Storage requirements and network bandwidth requirements ; S32: The desktop cloud resource scheduler calls the resource pool in the virtualization platform according to the computing power demand parameters to create a virtual machine instance ,in Indicates virtual machine instances; S33, virtual machine instance After successful creation, the required BIM software Deploy to the instance. The deployment process includes software installation, configuration, and import of related dependency files. S34. After the BIM software is deployed, the resource information of the virtual machine instance, the BIM software application information and the allocation status are recorded in the database. The record includes The unique identifier of the task, the number of resources assigned, and the task number ; S35, generate feedback information, and send the virtual machine instance Deliver relevant information to users; S36. During the deployment of the virtual machine instance, dynamically monitor the virtualized resource pool; S37. If resource conflicts or errors occur during the creation of virtual machine instances or the deployment of BIM software, record error logs and try to reschedule resources for repair or redeployment.

3. The BIM software automated full life cycle management method for a virtualized resource pool according to claim 1, characterized in that: The S4 comprises the following steps: S41. When the physical resources in the resource pool cannot meet the demand, the desktop cloud resource scheduler calls the dynamic association adaptive resource coordination algorithm; for each task Build time dependent resource requirement vector: ;in, For the task In time The number of CPU cores required; For the task In time The amount of memory required; For the task In time The amount of storage required; For the task In time Required network bandwidth; S42. Introducing the dynamic correlation matrix , combined with the changing trend of historical task requirements; used to measure the task and tasks The resource demand correlation between: ； The first measurement task and tasks The similarity of resource requirements at each moment captures the current resource requirements; the second measurement task and tasks The resource demand change trend is captured through the time derivative to capture the dynamic changes of history; Used to control the impact of historical demand change trends on relevance; S43. Calculate the dynamic priority coefficient for each task based on the dynamic relevance of the task , used to determine the priority of tasks in resource allocation; the calculation formula of the priority coefficient is: ； in, For the task In time Priority; Task and tasks Dynamic correlation of S44, introduce task adaptive adjustment coefficient , which is used to make real-time adjustments based on the actual resource usage and expected demand of the task. The adjustment formula is: ； in, For the task Adaptive adjustment coefficient of To adjust the difference between actual use and expected use; For the task In time The actual resource usage of For the task the expected resource requirements; To control the correlation between tasks Impact on adaptive regulation; S45. According to the priority coefficient of the task and adaptive adjustment coefficient , dynamically calculate the resource allocation for each task ; S46. To optimize resource allocation, a spatiotemporal feedback control mechanism is introduced to adjust the resource allocation of tasks through real-time feedback; S47. Based on the execution of the tasks, the spatiotemporal feedback control mechanism is used to continuously optimize resource allocation.

4. The BIM software automated full life cycle management method for a virtualized resource pool according to claim 1, characterized in that: The S5 comprises the following steps: S51. When resource coordination still cannot meet the demand, BIM resource application is added to the task queue; a hierarchical computing model is constructed according to the different resource requirements of the task; each task The computing power demand vector is decomposed into ;in, For the task In time CPU computing power requirements; For the task In time Memory computing power requirements; For the task In time Storage and computing power requirements; For the task In time The network computing power required; For the task In time The energy demand, which represents the energy consumed by the task; S52. Introduce a high-dimensional time-varying feedback driven model to dynamically adjust the hierarchical computing power requirements of tasks based on real-time feedback information; define the time-varying feedback coefficient matrix , which is used to regulate the dynamic changes of hierarchical requirements of tasks over time, is derived as follows: ； in, is the identity matrix; is the feedback adjustment coefficient; is the feedback frequency; is the phase offset; is the nonlinear feedback attenuation coefficient; S53, according to the time-varying feedback coefficient matrix , dynamically adjust the hierarchical computing power requirements of tasks; S54, further optimize the resource allocation of tasks through the dynamic collaborative hierarchical model; collaborative hierarchical matrix Representation Task and tasks The synergy effect in computing resource stratification is derived as follows: ； in, is the eigenvalue of the collaboration matrix; the first term represents the task and tasks The synergistic effect of computing power requirements changing over time; the second term controls the differences in resource requirements between different tasks through nonlinear decay; To control the impact of differences in resource requirements on synergy; S55. Adjust requirements based on task feedback and the collaborative hierarchical matrix , calculate the final resource allocation , the allocation formula is: ； in, For the task The final resource allocation obtained; is the collaborative layering matrix; S56. To further optimize resource utilization, a nonlinear spatiotemporal feedback control mechanism is introduced to dynamically regulate resource allocation by combining temporal and spatial feedback. The derived formula is as follows: ； in, is the spatiotemporal feedback adjustment coefficient; is the spatial regulation function; is the spatial position attenuation coefficient; is the initial spatial position of the task; S57. Through the spatiotemporal feedback control mechanism, the resource allocation of tasks is dynamically monitored and adjusted, so that tasks can achieve efficient resource hierarchical reuse and regulation when the resource pool is limited.

5. The BIM software automated full life cycle management method for a virtualized resource pool according to claim 1, characterized in that: The S6 comprises the following steps: S61. Monitor the usage status of virtual machine instances and collect resource usage data of each virtual machine instance, defined as , which includes CPU usage , Memory usage , Storage usage and network bandwidth usage ; S62. By evaluating the resource usage data of the virtual machine instance , computing resource utilization , and analyze whether the resources in the virtual machine instance are fully utilized; S63, when the resource utilization of the virtual machine instance Below the preset threshold for a long time When the resource of the virtual machine instance enters the recycling state, it is determined whether the resource of the virtual machine instance enters the recycling state; S64: For virtual machine instances that meet the recycling conditions, unused resources are recycled from the instances through a resource recycling mechanism to generate a recycled resource vector , indicating a virtual machine instance The amount of recycled resources in S65. Recycled resources The resource pool is re-added and resources are dynamically allocated based on new task requirements. The allocation is based on the task priority and the resource requirements of the current task, and the amount of resources reallocated to the new task. ; Allocate based on available resources in the resource pool; S66. After the resources are reallocated, the resource usage of the new task is monitored in real time, and resource usage data of the new task instance is collected and analyzed; S67. Further optimize and dynamically adjust resource allocation between tasks according to the resource usage status of the new task.

6. The BIM software automated full life cycle management method for virtualized resource pool according to claim 1, characterized in that: The S7 comprises the following steps: S71, real-time collection task Resource requirements, building a task-resource bidirectional response matrix , used to capture tasks About Resources The time-varying effect of is defined as follows: ； in, For the task In time The amount of resources required; For the task In time The rate of change of resource demand; For resources The time-varying response function of Indicates the change from the initial time to the current time; S72. Resources The time-varying response function It represents the dynamic response of resources to changes in task requirements, taking into account resource availability and load fluctuations. The derived formula is: ； in, For resources In time The actual amount of resources available; For resources In time The maximum available capacity; For resources Minimum resource limit; To adjust the attenuation coefficient; S73, based on the two-way response of tasks and resources, using nonlinear resource control function Dynamically adjust resource allocation between tasks; resource allocation priority Defined as: ； in, It is a two-way response matrix of tasks and resources; For current time Total available resources in the resource pool; For the task Resource requirements at the current time; A small constant to avoid zero denominator; S74. In the process of resource allocation, the actual usage of tasks is dynamically adjusted through the feedback control mechanism; feedback control function Adjust based on actual usage of tasks and expected demand; S75. Final resource allocation for the task Integrated feedback control function and nonlinear resource regulation functions , defined as: ; S76. Continuously adjust resource allocation priorities based on real-time feedback so that tasks can obtain sufficient resource support in a timely manner when resource requirements change; real-time adjustments are determined by task feedback information and the availability of resource pools; S77. Analyze the execution feedback of the task and further optimize the time-sharing reuse strategy of computing resources.

Images