99 results about "Heterogeneous cluster" patented technology

The invention discloses a hybrid attack defense control method and system for a heterogeneous cluster in an urban confrontation environment, terminal equipment and a medium, and relates to the technical field of unmanned platform cluster control, and the method comprises the steps: constructing an ideal system model of an unmanned platform cluster comprising a leader and a plurality of followers, constructing an information physical hybrid attack model based on the model; using the attack model to simulate an attack behavior of an attacker on an ideal system to obtain an attacked system model; based on an attacked system model, constructing a distributed elastic security estimator with a compensation mechanism, compensating attack influence for each follower and estimating an expected position; and based on the expected position of the follower, constructing a distributed elastic safety controller with a compensation mechanism, and controlling the follower. By designing the estimator and the controller, attack interference is counteracted, control input is generated, and safe collaboration of the heterogeneous nonlinear unmanned cluster under the cyber-physical hybrid attack is guaranteed.

An energy-conscious workflow planning system based on LLM with dynamic resource allocation, consisting of: a workflow input interface configured to receive workflow-directed acyclic graphs (DAGs), energy budget constraints, system performance constraints, and natural language requests from human operators; a large language model (LLM) logic module connected to the workflow input interface and configured to analyze the workflow specifications and system constraints in natural language, generate energy-conscious planning recommendations based on the analyzed workflow specifications, and provide explainable planning rationales in natural language; a reinforcement learning-based scheduling unit connected to the LLM reasoning module and configured to: receive scheduling recommendations from the LLM reasoning agent, fine-tune task-resource assignments by dynamically adapting to runtime variations, and perform online resource redistribution under runtime variability; an energy monitoring unit configured to: continuously monitor CPU and GPU utilization in heterogeneous clusters, track power consumption and thermal limits per node, and generate energy profiles for system components; a multi-objective optimization engine configured to: perform a Pareto-optimal scheduling analysis that balances energy consumption, lead time and reliability, apply statistical and AI-supported trade-off analyses and ensure optimal resource allocation based on Pareto frontier analysis; a dynamic resource allocation unit configured to: use predictive models that incorporate LLM inferences and feedback from reinforcement learning, reassign tasks between nodes and clusters while minimizing energy consumption and improving system throughput based on the predictive models; a performance optimization module configured to optimize scheduling decisions using multi-criteria optimization analysis; and a user interface that allows human operators to override and refine planning strategies in real time based on verifiable planning reasons.

The invention discloses an execution time aware computing power network heterogeneous GPU cluster deep learning task node allocation method and system. The method comprises the following steps: firstly, based on a deep learning task, extracting and preprocessing task features and available node features; secondly, a sampler equally divides new tasks without historical data to available nodes, and each node performs mixed sampling on the tasks until all the tasks estimate execution time data; taking execution time data as a training set, taking the task features and the node features as a test set, and using a regression decision tree model to predict the execution time of the task on each node; performing task allocation on each node by using a cost search algorithm and a short job total JCT priority strategy; and finally, periodically monitoring node resources released in the cluster to obtain an optimal node allocation result. According to the method, task delay and total task JCT are remarkably reduced, cluster node resource changes are monitored in real time, and the resource utilization rate is increased.

The invention provides an asymmetric segmentation scheduling system and method in a heterogeneous GPU cluster, and the method comprises the steps: S1, checking the features of an incoming request, and grouping the incoming request into different request buckets according to the token length; s2, in a heterogeneous GPU cluster environment, optimizing a large language model reasoning instance by adopting a double-layer strategy; and S3, calculating the matching degree of the request buckets and the big language model reasoning instances, and scheduling different request buckets to the big language model reasoning instance with the highest matching degree according to a calculation result. According to the method provided by the invention, the model layer can be asymmetrically segmented according to the computing power and the video memory capacity of each GPU on the premise of satisfying the model parallelism degree constraint, the dynamic balance of the execution duration between stages is realized, assembly line cavitation bubbles are fundamentally reduced, and the overall throughput rate is improved.

Systems and methods are described herein to orchestrate the execution of an application, such as a machine learning or artificial intelligence application, using distributed compute clusters with heterogeneous compute resources. A discovery subsystem may identify the different compute resources of each compute cluster. The application is divided into a plurality of workloads with each workload associated with resource demands corresponding to the compute resources of one of the compute clusters. Adaptive modeling allows for hyperparameters to be defined for each workload based on the compute resources associated with the compute cluster to which each respective workload is assigned and the associated dataset.

The invention discloses a GPU cluster resource allocation method and device, equipment and a storage medium, and relates to the technical field of GPU cluster resource allocation. According to the method, a hardware performance description vector is generated by fusing static hardware parameters and dynamic micro-benchmark test data, the limitation that the GPU performance is represented only by depending on the static parameters is broken through, and the actual operation capacity of different architecture GPUs in a heterogeneous cluster is accurately matched; task feature vectors are generated by extracting task calculation features and resource demands, and quantitative description of reasoning task resource consumption features is achieved; information of hardware, tasks and load dimensions is integrated through a machine learning model, performance degradation characteristics during multi-task parallel are effectively captured, and the accuracy of execution time prediction is improved; scheduling decision operation including candidate node screening, comprehensive cost evaluation and resource reservation backfilling is executed in combination with the predicted execution time, and the task execution efficiency and cluster load balancing are both considered.

The embodiment of the invention is suitable for the technical field of artificial intelligence, and provides a re-calculation training strategy generation method, electronic equipment and a computer program.The method is applied to a heterogeneous cluster and comprises the steps that cluster information of the heterogeneous cluster and model feature information of a to-be-trained model are determined; for each storage and calculation resource in the heterogeneous cluster, according to the cluster information and the model feature information, re-calculation time information and re-calculation performance requirements are determined; determining a re-calculation time information characteristic value under the condition that the re-calculation performance demand is not greater than the performance limit value of the storage and calculation resources; and determining a recalculation training strategy for the to-be-trained model according to the recalculation time information feature value corresponding to each storage and calculation resource. According to the embodiment of the invention, the adaptive re-calculation training strategy can be determined for each storage and calculation resource of the heterogeneous cluster, and the model training efficiency and throughput are improved by adopting the re-calculation training strategy corresponding to each storage and calculation resource to carry out model training.

The invention provides a complex construction site construction equipment control system and method, and the system constructs a basic state semantic model of each type of equipment, and covers all perception and control instruction data; the comprehensive management and control platform dynamically extracts and issues one or more data packet formats from the basic model according to construction scenes, areas and equipment types, and fine adjustment of sensing information and instruction formats is achieved; the edge computing device is deployed at an equipment end or a cluster end and is responsible for dynamic mapping analysis, redundancy removal, priority screening and unified protocol packaging of a multi-heterogeneous protocol; the equipment end reports a null instruction sensing data packet, the comprehensive management and control platform generates an optimal control instruction, compresses recent sensing data and then issues the compressed recent sensing data in the same data packet format; the equipment end decides whether to execute the instruction or not, if not, problem expression is fed back, and a safe closed loop is formed; in a cluster scene, gathering fusion and instruction distribution of multi-level edge computing devices are supported, and efficient collaboration of heterogeneous clusters is achieved.

The invention discloses a method and a system for simplifying large model reasoning service deployment in a heterogeneous cluster environment, mainly relates to the technical field of service deployment, and is used for solving the problems of repeatability cost of heterogeneous adaptation, dependence on manual allocation of containers to specific nodes during containerization deployment and version library compatibility in an existing scheme. And crash is caused, and dynamic resource allocation based on load characteristics is lacked. Comprising the steps of performing preset mirror image condition matching on a node hardware feature tag and a model service demand tag of an implementation node and a pre-built reasoning service container mirror image in a mirror image warehouse; when the pre-constructed reasoning service container mirror image with the matching degree of 100% does not exist, dynamically constructing a customized reasoning service mirror image, and storing the customized mirror image in a mirror image warehouse as the pre-constructed reasoning service container mirror image for implementing node matching; and pulling a pre-constructed reasoning service container mirror image for implementing node matching from the mirror image warehouse, mounting a standardized model file mirror image, and starting a reasoning service container.

Disclosed in the embodiments of the present application are a resource determination method and apparatus, and a program product and a storage medium. The method in the embodiments of the present application comprises: receiving an inference request; determining a first computing resource required for when a large model performs inference on the inference request; acquiring first resource information of a heterogeneous cluster; and on the basis of the first computing resource and the first resource information, determining a first inference resource from the heterogeneous cluster, wherein the first inference resource is used by the large model to perform inference on the inference request. In this way, for an inference request received in real time, a computing resource required for performing inference on the inference request is determined in real time, which enables dynamic determination of computing resources corresponding to inference requests of different lengths. Thus, an inference resource corresponding to the inference request can be dynamically determined on the basis of the computing resource, and the corresponding inference resource can be more accurately determined from the heterogeneous cluster, so that inference is performed on the inference request on the basis of the inference resource, such that an inference process of the large model can avoid being affected.

The invention discloses a heterogeneous cluster parallel multi-stage fuzzy job scheduling method, which comprises the following steps of: receiving a processing request which is submitted by a user and contains multi-stage jobs, and modeling task execution time, data transmission time and request deadline into triangular fuzzy numbers, constructing a scheduling model taking the minimization of the total lease cost and the minimization of the request tardiness as targets; carrying out global exploration by adopting an improved second-generation non-dominated sorting genetic algorithm to generate parent and offspring populations; based on population similarity threshold judgment, dynamically triggering local search guided by a multi-agent near-end strategy optimization algorithm, and adaptively selecting a local search operator for each individual to generate an adjacent population; combining various populations, performing non-dominated sorting and crowding distance calculation, and screening out a new generation of populations; and iterating the process until convergence, and outputting a Pareto optimal solution set. According to the method, the problem of multi-target scheduling with fuzzy time variables in a heterogeneous environment is effectively solved, and the quality of a scheduling scheme and the algorithm search efficiency are improved.

The invention discloses a heterogeneous GPU cluster-oriented efficient collective communication method and device, and the method comprises the steps: obtaining a target communication operator set and a physical topology corresponding to a heterogeneous GPU cluster, and determining an initial state constraint and a target state constraint; the scheduling time cost of each communication scheme is determined, and the communication scheme corresponding to the minimum scheduling time cost in the multiple scheduling time costs is selected as the efficient collective communication mode of the heterogeneous GPU cluster. According to the method, the communication scheme corresponding to the minimum scheduling time cost of the heterogeneous GPU cluster is determined to serve as the efficient collective communication mode of the heterogeneous GPU cluster based on the actual conditions of topological structure difference, link bandwidth imbalance and the like in the heterogeneous GPU cluster environment; it is ensured that the communication process is not limited by the bandwidth bottleneck, and system resource utilization efficiency and parallel training performance are prevented from being limited.

The invention relates to the technical field of computers, and discloses a tail delay optimization job scheduling method and system based on a heterogeneous GPU cluster. The method comprises the following steps: constructing a cluster physical topological graph containing link delay, bandwidth and hop count; predicting a job communication demand graph through static code analysis and a graph neural network; executing topology matching scheduling, and preferentially deploying a high communication task pair on a high-speed interconnection link in a node or a low-delay link on the same rack; and tail delay is monitored during operation, and cost-aware local rescheduling is triggered. The system comprises a physical topology modeling module, a communication demand prediction module, an affinity scheduling module and a dynamic rescheduling module. Through active prevention and closed-loop optimization, job tail delay is reduced, and heterogeneous cluster service quality and resource utilization efficiency are improved.

A method for managing a workload migration includes: receiving a request from a user that wants to migrate a workload from a source information handling system (IHS) to a target IHS; analyzing the request and a first IHS configuration list to infer the source IHS' configuration and criticality of the request; making, based on the analyzing of the request and first IHS configuration list, a first determination that the request is non-critical; making, based on the first determination, a second determination that the target IHS does not have the source IHS' memory configuration; and waiting, based on the second determination, until the target IHS or a second target IHS has the source IHS' memory configuration; making a third determination that the second target IHS has the source IHS' memory configuration; and migrating, based on the third determination, the workload from the source IHS to second target IHS.

A computer-implemented scheduling method for accelerator hardware includes using a computational graph that splits jobs to be executed by the accelerator hardware into atomic compute tasks, using a scheduler to individually schedule and / or migrate each task for execution to different machines and / or accelerators at job runtime, and using a computer daemon to allocate memory and execute kernels for each task on the respective machines and / or accelerators.

The embodiment of the invention provides an electromagnetic scattering calculation method based on a heterogeneous GPU cluster. The method is applied to the field of computational electromagnetism, and comprises the following steps: constructing a hierarchical bounding volume geometric acceleration structure of a target object and adding an edge index, and meanwhile, completely copying and distributing data of the acceleration structure to a video memory of each computational node in a heterogeneous GPU cluster; generating a random ray path starting from an emission source, modeling an electromagnetic scattering process as a ray path set in a probability space, and generating a ray direction through an importance sampling strategy; determining a static scheduling strategy for the ray batch based on the calculation cost of pre-sampling and geometric enhancement, and carrying out non-uniform distribution on task tiles according to the heterogeneous GPU calculation power; and monitoring the execution state of the heterogeneous GPU cluster in real time, and dynamically adjusting the distribution strategy of the residual ray tasks based on execution feedback. According to the method, the calculation overhead can be remarkably reduced while the calculation precision is ensured, and the efficiency and expandability of complex target electromagnetic scattering calculation are improved.

The invention provides a heterogeneous cluster model update task scheduling method based on reinforcement learning, which mainly improves the scheduling efficiency of resources in an unmanned cluster, balances the task processing performance of each resource in the unmanned cluster, and solves the scheduling decision problem of model update tasks in a heterogeneous unmanned cluster. According to the scheme, before an unmanned cluster starts distributed training, scheduling decision making is firstly carried out on a training task of a single model, then task scheduling is executed, and finally distributed training is carried out; the system takes model training completion time and cluster total energy consumption as optimization targets; according to the method, the advantages of Dirichlet distribution and reinforcement learning are combined, task scheduling constraint conditions can be effectively met, meanwhile, the method has high exploration capacity, and therefore an efficient task scheduling strategy is generated; compared with a traditional heuristic algorithm and other reinforcement learning methods, the task scheduling scheme can be directly generated for the cluster without complex mathematical modeling, and the complexity and cost of implementation and maintenance are reduced.

The invention provides a mimicry transformation system based on a service component, and the system comprises the steps: determining N distribution requests after determining the installation of a service in a new service request, matching N heterogeneous cluster nodes, creating corresponding M kubernates cluster connections according to the matching of the N heterogeneous cluster nodes and corresponding heterogeneous information, and generating a command to create N service components. The method comprises the steps of storing a cluster node path and service component information into a database table, obtaining relevant configuration and role information of service components, generating serviceRoleUi, determining an installation sequence of each service component according to a dependency relationship existing among the service components, generating a new service command according to the installation sequence, and installing N service components, and different processing modes are designed according to N response results returned by N service component requests, so that the safety characteristic of the service component is improved, and the anti-attack capability of the whole platform is enhanced.

The invention discloses a heterogeneous UAV cluster air-based task chain closed optimization method, and belongs to the technical field of UAV cluster cooperative control. Firstly, task chain nodes and information flow are instantiated based on specific task parameters, and an initial closed task chain is constructed; dimensionality reduction is carried out on task points through AGNES clustering to obtain task groups, and UAV-task group matching is realized in combination with an efficiency function; a task chain path is dynamically adjusted through a closing time model, a final result is generated by optimizing a task chain through an execution precision model, and closing optimization is achieved. According to the method, a double-layer optimization mechanism for decoupling task topology arrangement and task chain attribute closing is designed, the decision space complexity is reduced through a divide-and-conquer method, and rapid response of dynamic task elements is achieved; rapid construction, dynamic adjustment and accurate closing of the task chain are realized, and the task execution efficiency of the heterogeneous UAV cluster is improved.

The invention relates to the technical field of deep learning models, and particularly provides a heterogeneous cluster-oriented multi-dimensional collaborative division and communication optimization distributed training method. The method comprises the steps that heterogeneous equipment and a model are analyzed through an analysis module, and input data are provided for optimization solution; a three-dimensional collaborative optimization division algorithm is utilized to bring selection of an activation value re-calculation strategy into a division optimization process, and video memory constraints are converted into soft constraints of calculation cost relaxation; according to the method, topology sensing self-adaptive communication is carried out, communication transmission modes are dynamically switched on the basis of divided link attribute marks, and the throughput and stability of large-model distributed training are improved.

The embodiment of the application is suitable for the field of artificial intelligence technology, and provides a re-computation training strategy generation method, an electronic device and a computer program. The method is applied to a heterogeneous cluster, and includes: determining cluster information of the heterogeneous cluster and model feature information of a to-be-trained model; determining re-computation time information and re-computation performance requirements of each storage-computing resource in the heterogeneous cluster according to the cluster information and the model feature information; determining a re-computation time information characteristic value in a case where the re-computation performance requirements are not greater than a performance limit value of the storage-computing resource; and determining a re-computation training strategy for the to-be-trained model according to the re-computation time information characteristic value corresponding to each storage-computing resource. The embodiment of the application can determine an adaptive re-computation training strategy for each storage-computing resource of the heterogeneous cluster, and improve the model training efficiency and throughput by using the re-computation training strategy corresponding to each storage-computing resource for model training.

The application discloses a heterogeneous computing power cooperative adaptation method based on distributed pooled computing power, and relates to the technical field of heterogeneous computing power resource scheduling; basic data sets are collected from a computing power heterogeneous platform, time sequence characteristic sets and scene characteristic sets are obtained through standardization processing; relying on a computing power prediction model composed of a basic time sequence prediction layer, a scene characteristic enhancement layer and an output fusion layer, the computing power demand trend of each heterogeneous cluster is accurately predicted; the demand priority is set in combination with the computing power growth rate threshold and the scene label; then, a scheduling decision is generated through a coordination scheduling model, and the resource allocation is optimized with the aid of a dynamic adaptive adjustment mechanism; the application realizes fine representation of heterogeneous computing power and accurate matching of tasks, breaks the rigid limitations of the adaptation strategy of traditional schemes, effectively improves the accuracy of heterogeneous computing power adaptation and the comprehensive utilization rate of resources, significantly reduces the performance fluctuation of core businesses, and achieves the dynamic balance of efficient resource utilization and stable business operation.

The application discloses a VLLM-based heterogeneous cluster distributed reasoning cooperation method and system, and the method comprises the following steps: S1, generating a heterogeneous device performance image signal through a performance probe arranged in each computing unit in the cluster; S2, performing non-uniform task division according to the heterogeneous device performance image signal and combining a calculation graph structure of a to-be-reasoned model to form an optimal task scheduling strategy signal for a heterogeneous environment; S3, generating a task allocation and loading instruction signal based on the optimal task scheduling strategy signal; S4, coordinating each heterogeneous computing unit to perform reasoning calculation in a distributed reasoning execution process to generate a distributed cooperative reasoning signal; and S5, integrating and post-processing the distributed cooperative reasoning signal to output a final reasoning result. The VLLM-based heterogeneous cluster distributed reasoning cooperation method and system can solve the problems of low resource utilization and poor reasoning efficiency when a large model is run on a heterogeneous cluster.

The invention relates to a scheduling method which schedules deep learning jobs through a primitive-dual framework and a dynamic programming algorithm in a heterogeneous GPU cluster and can meet different deadline requirements of the jobs. According to the method, on-line analysis and historical data are combined in a heterogeneous GPU cluster environment, so that the overhead of obtaining the job throughput is reduced; according to the method, job scheduling and job placement are decoupled, the complexity of job scheduling is reduced, meanwhile, a simple and effective job placement scheme is designed, and the degree of resource fragmentation is effectively reduced; a scheduling target is modeled in a scheduling module, reward value functions are respectively designed for strict deadline operation and soft deadline operation, an optimization problem is constructed by taking maximization of an overall reward value as the scheduling target, and strict deadline requirements and soft deadline requirements of the operation are considered at the same time; and reconstructing the target optimization function into an integer linear programming problem, and solving by using a primitive-dual framework and a dynamic programming algorithm to ensure the theoretical effectiveness of the solution.

This invention relates to the field of wireless communication network technology and provides a heterogeneous stream processing cluster interconnection device in a software radio system. By designing a heterogeneous computing power cluster interconnection architecture in which the radio frequency front-end layer, heterogeneous computing power pool layer, core interconnection layer, and cluster management layer work together, and with the core structure design of heterogeneous cluster internet gateway + high-speed cluster non-blocking switching + global cluster high-precision synchronization + layered cluster deployment, it breaks through the technical bottlenecks of existing heterogeneous computing power cluster integration from the hardware level, and achieves significant improvements in cluster collaboration performance, synchronization accuracy, transmission efficiency, compatibility, reliability, and engineering feasibility, effectively improving the cluster interconnection performance of the heterogeneous stream processing cluster.

The invention discloses a distributed unmanned cluster cooperative control system, which belongs to the technical field of unmanned system cooperative control, and comprises a heterogeneous cluster composed of various types of unmanned platform nodes, and the cluster comprises an unmanned aerial vehicle node, an unmanned ship node and an unmanned underwater vehicle node; the intelligent control units run on the unmanned platform nodes in a distributed manner and are used for realizing autonomous decision making and local collaboration of the platform; and the dynamic self-organizing communication network is connected with each node in the cluster and is used for realizing information interaction among the nodes. The system provided by the invention has extremely high robustness and survivability, a decentralized architecture eliminates single-point faults, failure or interference of partial nodes does not affect the core function of a cluster, the system is particularly suitable for an adversarial or severe environment, and a distributed task market mechanism enables tasks to be dynamically matched to the most suitable platform, so that the system has high robustness and survivability. The overall operation efficiency and the resource utilization rate are improved, and the cooperative logic of heterogeneous platforms such as air, sea and underwater platforms is effectively unified through a standardized task interaction protocol.

This application provides a method, apparatus, electronic device, and storage medium for aggregated communication scheduling, relating to the field of artificial intelligence technology. The method includes: dividing the communication process of an aggregated communication task into three communication stages; in the first communication stage, performing aggregated communication within each homogeneous sub-cluster; in the second communication stage, performing point-to-point communication between target computing nodes between at least two homogeneous sub-clusters; and in the third communication stage, performing aggregated communication within each homogeneous sub-cluster. Based on concurrently executed homogeneous communication task queues and heterogeneous communication task queues, the method schedules each computing node in the heterogeneous cluster to exchange multiple data blocks sequentially in the three communication stages. The method and apparatus provided in this application realize aggregated communication between heterogeneous computing nodes; by allowing different communication stages of different data blocks to be executed in parallel, the total time required to complete the entire aggregated communication task is significantly shortened, and the overall throughput of distributed computing is improved.

This invention relates to a heterogeneous construction equipment cluster control system and method based on a VLA model, belonging to the field of building construction technology. The system includes a cluster multimodal perception unit, an elevation benchmark fusion unit, an equipment status modeling unit, a multimodal decision control unit, an instruction allocation and safety verification unit, a low-level execution control unit, and a human-machine interaction and remote monitoring platform. By introducing innovative technical solutions such as visual language action models, multi-source data fusion, hybrid control, and safety verification, this invention achieves high-precision synchronous jacking and stable control of the core tube and mega-column formwork cluster, and high-precision collaborative control of the platform's flatness and vertical attitude. This improves the intelligence level and stability of the heterogeneous cluster synchronous control, reduces the relative deformation and stress concentration risks of the equipment cluster connection structure, provides a more efficient and safer collaborative control method for super high-rise construction, and ensures the smooth implementation of the project.

The invention discloses a cloud native multi-architecture scheduling method and system for heterogeneous nodes, and belongs to the technical field of cloud native, and the method comprises the steps: recognizing multi-dimensional architecture features of heterogeneous node registration information, marking the features as node tags, and constructing a multi-dimensional feature system; constructing a multi-architecture mirror image, and generating a unified mirror image address; determining an optimal scheduling node in response to a multi-architecture deployment and scheduling request; according to the cloud native multi-architecture scheduling method and system for the heterogeneous nodes, unified management of the heterogeneous nodes and intelligent scheduling and efficient operation and maintenance of multi-architecture mirror images are realized, so that a scheduling decision is upgraded from dependence on a single architecture label to comprehensive judgment based on the real state and trend of the nodes, and resource mismatching is effectively avoided; the resource utilization rate and the load balance degree of the heterogeneous cluster are improved; the scheduling precision and the resource utilization rate are improved; multi-architecture adaptation manual intervention is eliminated; the operation and maintenance complexity is reduced;

The invention relates to a cluster fusion feature generation method, an application method and a system based on feature interaction, and solves the problem that heterogeneous computing scheduling time sequence features and associated features are transmitted unidirectionally or fused without difference and collaborative modeling cannot be realized in the prior art. The method comprises the following steps: acquiring computing power data and associated data of each node of a remote heterogeneous cluster, performing standardization processing, determining a current standardization feature, and acquiring a current basic time sequence feature by using an LSTM network and a GAT network; according to the historical standardized features, the current standardized features, the historical basic association features and the current basic association features, feature interaction and time sequence statistics are carried out to obtain current association-time sequence splicing features and current time sequence statistical features, then current optimized time sequence features are obtained, and current optimized association features are obtained; and determining a current cluster fusion feature of each node. According to the method, bidirectional enhancement of the time sequence features and the associated features is realized, precise collaborative modeling is realized, and heterogeneous calculation scheduling precision and decision-making efficiency are improved.