163 results about "Parallel optimization" patented technology

The invention relates to the technical field of control, and particularly discloses a multivariable energy efficiency optimization control system for a heating furnace, which is used for solving the problems of local overheating, non-uniform temperature and difficulty in accurate positioning and compensation of heat loss in the operation of the existing cracking heating furnace. Comprising a parameter detection module, a multivariable coupling modeling and simulation module, an optimization control module and an execution and feedback module. According to the method, dynamic digital twinning is constructed through multi-modal online sensing and data assimilation, a Pareto frontier solution is generated based on model prediction control and improved NSGA-II parallel optimization, and the weight is adaptively adjusted; and when the hot spot / cold spot is triggered, a quadric surface fitting compensation strategy is implemented and issued for execution, so that high-precision simulation prediction, precise closed-loop control and real-time online energy efficiency optimization are realized.

The invention relates to the technical field of artificial intelligence, in particular to a large model and multi-agent collaborative decision-making method based on dynamic knowledge flow, which comprises the following steps of: analyzing a static knowledge and dynamic information fusion relationship through joint modeling, extracting a hierarchical structure of equipment constraints and environment variables, identifying constraint conflicts and deviations in task decomposition, and obtaining a multi-agent collaborative decision-making result; screening a consistency decomposition direction, extracting a task constraint parallel optimization theory, correcting constraint conflicts, evaluating consistency changes, and outputting a collaborative task convergence robust state identifier. According to the method, by integrating static knowledge and dynamic information and optimizing understanding of task decomposition and equipment constraints, the collaborative decision-making capacity of multiple agents in a complex environment is enhanced, the conflict and deviation processing capacity in the task execution process is improved, the accuracy and consistency of tasks are enhanced, and the convergence and stability of task targets are improved; the robustness of multi-agent cooperative work is promoted, and finally more efficient resource utilization and task completion effects are achieved.

The invention belongs to the technical field of additive manufacturing, and particularly relates to a multi-scale parallel optimization method for a lightweight structure based on lattice discrete optimization. According to the method, through multi-scale parallel optimization design, a macro structure and a micro lattice structure are described through geometric parameters of a movable deformation rod piece, an improved two-value coding parameterization method, called a BCP method for short, is adopted to solve discrete optimization of the micro lattice structure, and geometric parameters of an optimization result are easy to extract.

The invention discloses a power distribution network photovoltaic openable capacity dynamic evaluation method fusing voltage stability margin and neural network optimization, and aims to solve the problems that a traditional method does not fully consider dynamic stability and is low in calculation efficiency. Firstly, a prediction method combining kernel density estimation and quantile regression is adopted to accurately quantify the uncertainty of distributed photovoltaic output. The core innovation of the method is that on the basis of traditional security constraints, a static voltage stability margin (VDSM) is introduced as a key constraint condition, and a double-layer interval analysis model capable of guaranteeing the dynamic stability of a power grid is constructed. Secondly, in order to efficiently solve, the invention provides a framework of'neural network pre-screening + parallel optimization ': after a model is decomposed into optimistic sub-problems and pessimistic sub-problems through an interval decoupling technology, massive candidate solutions are quickly screened by utilizing a neural network model, so that a feasible solution space is greatly reduced, and the solution efficiency is improved; and carrying out parallel optimization solution on the sub-models in combination with an improved particle swarm optimization algorithm.

A method for topological design optimization in which a number of objective scattering(S) parameters are initially decomposed into a product of smaller devices (primitives). Each of the primitives are optimized in parallel using inverse design; and the topologies of the smaller devices are then composited into a final device design region, in which the final device design region is an initialization of a final optimization, advantageously saving computation time. According to at least one embodiment, the herein described optimization procedure can be utilized in order to design a composite power combiner that is essentially phase-insensitive.

The invention discloses a photovoltaic optimization regulation and control method and device based on an MPPT technology, and particularly relates to the technical field of photovoltaic power generation control, and the method specifically comprises the following steps: S1, full-link operation state synchronous collection, S2, DC bus ripple feature extraction, S3, multi-source disturbance quantitative evaluation, S4, cooperative control parameter decision making, and S5, grid-connected signal synthesis modulation. A multi-source disturbance quantitative evaluation system is adopted, the irradiance change gradient, the frequency ratio and the switching noise contribution ratio are subjected to multi-dimensional fusion, a dynamic weight distribution mechanism is established, and parallel optimization of MPPT mode selection, disturbance step length adjustment and PWM phase shift angle is achieved through a cooperative control parameter decision architecture. A response delay bottleneck existing in a traditional serial decision mode is broken through, and a ripple compensation component is dynamically injected while stable output of fundamental current is maintained based on a grid-connected signal modulation strategy of vector synthesis.

The present application belongs to the technical field of additive manufacturing, and particularly relates to a lightweight structure multi-scale parallel optimization method based on lattice discrete optimization. The present application uses the geometric parameters of movable and deformable rods to describe macroscopic structures and microscopic lattice structures through multi-scale parallel optimization design, and uses an improved double-value coding parameterization method, referred to as BCP method, to solve the discrete optimization of the microscopic lattice structure and easily extract the geometric parameters of the optimization results.

The invention provides an attitude control method, system and equipment of an underwater leveling machine and the underwater leveling machine, and relates to the technical field of ocean engineering. The method comprises the following steps: establishing a dynamic model; constructing a physical information neural network based on the dynamic model; constructing a digital twinborn body of the leveling machine, and performing simulation verification on the attitude error prediction result in the digital twinborn body; based on a simulation verification result, taking control parameters of the underwater leveling machine as optimization variables, performing parallel optimization on a plurality of control targets of the underwater leveling machine, and generating a control solution set; and determining a target control parameter combination from the control solution set, and generating a control instruction for controlling the underwater leveling machine to perform attitude adjustment based on the target control parameter combination. According to the method, the reliability of attitude control of the underwater leveling machine can be improved through prediction of the integrated physical information neural network, simulation verification of the digital twin and multi-objective optimization.

The invention relates to a deep learning model reasoning method and device, computer equipment and a storage medium. The method comprises the following steps: calling an inference framework matched with a domestic accelerator, and performing compilation optimization, parallel optimization, memory hierarchical optimization and deep fusion of calculation acceleration components on a deep learning model to obtain a target optimization model; compiling the target optimization model into an executable machine code of the domestic accelerator; and loading the executable machine code on the domestic accelerator, and executing a data reasoning process of the executable machine code on to-be-reasoned data to obtain a model reasoning result. By adopting the method, the problem that an existing general reasoning framework is difficult to directly adapt to the domestic accelerator can be solved, the calculation potential of the domestic accelerator is completely released, and the reasoning efficiency and the resource utilization rate are remarkably improved.

The invention provides a renewable energy power system supply-transmission-demand-storage collaborative optimization configuration method, and relates to the technical field of smart energy, and the method comprises the steps: obtaining basic data of a plurality of provinces and cities, including renewable energy resource data and auxiliary data; establishing a collaboration degree calculation model, respectively calculating the collaboration degree of each subsystem, calculating the overall collaboration degree based on the collaboration degree of each subsystem, and constructing a subsystem collaboration strength matrix to quantify the coupling relationship among the subsystems; establishing a multi-sub-population collaborative optimization architecture, and respectively generating an initial solution set of each sub-population by adopting a collaborative degree-oriented initialization strategy; adopting an improved sparrow optimization algorithm to carry out parallel optimization on each sub-population, and obtaining an optimal configuration result when a convergence condition is met; and outputting a supply-transmission-demand-storage collaborative optimization configuration scheme of the renewable energy power system according to the optimal configuration result. The overall operation efficiency and economical efficiency of the system can be improved.

The invention discloses a self-adaptive supervision control method for logistics storage scheduling, and relates to the field of intelligent scheduling, and the method comprises the steps: S1, collecting an observation value of a multi-source sensor, and calculating a confidence coefficient and a state estimation vector in combination with a storage state pattern library; s2, constructing capacity and order perturbation factors based on the global confidence and the state estimation vector, and generating a scene set; s3, calculating a delay index and congestion penalty in combination with a scheduling rule, forming a scheme score, and generating a main scheduling scheme and an alternative scheme; and S4, constructing a real-time key index according to the order execution difference value, monitoring execution in combination with a dynamic threshold value, and triggering scheme switching when the deviation continuously exceeds the limit. Through the synergistic effect of multi-scene adaptive modeling, real-time supervision closed-loop control and a parallel optimization mechanism, the adaptability, robustness and global optimality of the scheduling process are remarkably improved.

The invention provides a sewage plant water-energy-drug collaborative optimization method and system, and the method comprises the steps: obtaining the data of a technological process and a material transfer relationship of a sewage plant, constructing a graph network structure model with a technological unit as a node and material flow as an edge, and carrying out the preprocessing, thereby obtaining dynamic coupling graph structure data; a dynamic coupling graph neural network model containing a node feature coding layer, a time sequence coding module, a space message passing layer and an attention mechanism layer is constructed based on the data, and a prediction model capable of representing the dynamic coupling relation of the process unit is obtained through historical data training; then, a multi-objective optimization function which takes the lowest ton water treatment cost as an objective and covers water quality standard reaching, energy consumption and medicament dosage constraints is constructed; and in combination with the prediction model and the optimization function, the optimal operation parameters are solved through an optimization algorithm, and a whole-plant collaborative optimization decision scheme is generated. According to the invention, the dynamic coupling GNN prediction model and the virtual element multi-domain parallel optimization technology are integrated, and intelligent operation management of the sewage treatment plant is realized.

The invention discloses an image compression method based on a JPEG-LS (Joint Photographic Experts Group-Least Squares) parallel optimization algorithm, which comprises the following steps: calculating local gradient values of to-be-coded data and then merging to obtain a context index Q value, the to-be-coded data being a prediction error of a current pixel; grouping the data to be coded according to the context index Q value; if the to-be-coded number contained in the key group affects the parallelism degree, a controllable distortion value is introduced into the pixel value of the to-be-coded data by using an equalization algorithm, and the group serial number corresponding to the data in the key group is corrected; deploying processing units of parallel channels with the number equal to that of the groups, and scheduling the grouped data to be coded to the processing units to realize pipeline processing; integrating each group of data into coded and compressed data through code stream splicing; the image compression method based on the JPEG-LS parallel optimization algorithm is used for image compression, the system data size is low, and the satellite-ground transmission bandwidth pressure is small.

The invention provides a self-adaptive collaborative parallel optimization aviation complex structural member production scheduling method and system and a program product. The method comprises the following steps: presetting parallel algorithm related parameters; initializing a population, wherein the initialized population comprises a first scheduling scheme generated by using a random greedy heuristic algorithm; performing evolutionary optimization on the initialized population or the derivative population of the initialized population in parallel by utilizing a plurality of configured sub-threads to generate a new scheduling scheme; according to a comparison result of the current CPU utilization rate and the memory utilization rate and the target CPU utilization rate and the target memory utilization rate, adjusting the number of sub-threads which are running; according to the method, the problems that in the prior art, a scheduling scheme is not high in quality and low in optimization efficiency, and the utilization rate of computing resources is difficult to consider are effectively solved, the high-quality and high-adaptability scheduling scheme can be generated, the solving time is shortened, the computing resources are fully utilized, and the scheduling efficiency is improved. The production efficiency and the resource utilization rate are improved.

The invention relates to the technical field of large-model lightweight fine tuning, and discloses a parallel optimization method of a low-rank adapter and a task awareness scheduling system.The parallel optimization method comprises the steps that an increment matrix of the low-rank adapter is fragmented to a tensor parallel group according to rows, the tensor parallel group comprises a plurality of computing devices, and the computing devices are used for computing the increment matrix of the low-rank adapter; the fragmentation granularity is dynamically determined according to the equipment hardware capability and the dimension of the increment matrix; dynamically scheduling the tasks with strong conflicts to different task parallel groups based on the calculated inter-task gradient conflict coefficient; and for a plurality of tasks scheduled to the same task parallel group, adapter calculation is merged into unified large matrix operation by adopting a micro-batch processing technology, and LayerNorm and adapter projection calculation are merged into a single calculation kernel by adopting a kernel fusion technology. According to the method, communication redundancy and synchronization overhead in distributed training are reduced, task interference during multi-task parallel is effectively eliminated, and the problem of computing resource fragmentation is solved.

The invention discloses a communication computing parallel optimization method, a multiprocessor system, a medium and a program product, and the method comprises the steps: configuring a first computing core and a second computing core on a single task flow for a general matrix multiplication subtask allocated to a single processor; wherein the first calculation core is used for executing a general matrix multiplication subtask, and the second calculation core is used for executing a set communication task; the set communication task comprises a full accumulation operator or a protocol dispersion operator; then, starting scheduling is conducted on the first calculation core and the second calculation core according to a preset dependency mechanism, so that the general matrix multiplication subtask and the set communication task are executed asynchronously in an overlapped mode; according to the method, the problem of poor reusability of the original Kernel caused by intrusive modification of the GEMM or re-implementation of the Kernel can be effectively avoided through parallel optimization of GEMM calculation and ensemble communication operation, and the performance overhead of the processor is reduced.

The invention discloses a Fortran program parallel optimization method based on intelligent dependency analysis. The method comprises the following steps: firstly, constructing a parallel optimization system consisting of a loop extraction module, a loop nested relation analysis module, a semantic analysis module, an intelligent dependency analysis engine, a variable classification module and an instruction generation and injection module; the loop extraction module analyzes a nested relation and a variable action range of loops; the loop nesting relation analysis module determines a nesting relation between loops; the semantic analysis module constructs a row-level data access view; the variable classification module identifies private variables and reduction variables; the intelligent dependency analysis engine executes loop type check, I / O operation check and data dependency check; and the instruction generation and injection module generates a parallelization instruction and inserts the parallelization instruction into the source code to obtain a parallelized program source code. The method can solve the problems that an existing parallelization method is low in cyclic dependency relation recognition accuracy and safety, and parallelization errors cannot be accurately recognized.

The application relates to the technical field of server data storage, and discloses a processing system for improving server data storage speed, which comprises a data blocking module, a parallel optimization module, a performance monitoring module, a strategy matching module and a storage execution module, and can comprise a load self-learning module. The data blocking module blocks data streams according to a dynamic strategy and generates a distribution queue; the parallel optimization module generates an optimal storage node combination and a scheduling strategy according to the queue; the performance monitoring module collects real-time performance data and screens for abnormalities; the strategy matching module determines a target adjustment rule through multidimensional matching; the storage execution module drives a node to correct a path; and the load self-learning module optimizes a scheduling factor according to feedback data. The system realizes dynamic blocking, adaptive scheduling and real-time optimization, improves storage efficiency and stability, and is suitable for a server data storage scene.

The present application relates to a kind of efficient parallel optimization method and device considering the actual engineering constraint of horizontal well, method includes the following steps: S1 constructs water drive reservoir production optimization mathematical control model;S2 based on horizontal well engineering application condition and reservoir numerical model, the constraint judgment method of horizontal well is constructed;S3 based on the population in Latin hypercube sampling initialization algorithm, using the constraint judgment method of horizontal well is handled, database is constructed;S4 using the excellent individual in database forms temporary population, based on temporary population, Gaussian model is constructed;S5 based on differential evolution algorithm with different strategies obtains three sub-populations, and using the constraint judgment method of horizontal well is handled;S6 based on the pseudo-update strategy of temporary population, the potential individual of sub-population is obtained;S7 based on Euclidean distance, select the individual closest to current optimal individual, and carry out parallel numerical simulation;S8 updates database.

The invention provides a method for reasoning by using a large language model, a control device and a storage medium, and belongs to the technical field of large language models. The method comprises the steps that in the reasoning process of a target large language model, a weight matrix and input data of the target large language model are segmented into a plurality of data blocks; sequentially loading each data block in the plurality of segmented data blocks into a memory, and carrying out parallel optimization calculation on each data block; and combining the calculation result corresponding to each data block to obtain a reasoning result. Through block parallel computing, the reasoning performance of the large language model in a CPU environment can be remarkably improved, and an efficient and flexible solution is provided for large language model reasoning in a resource-constrained environment.

The invention discloses a permanent magnet synchronous motor multi-target model prediction control method based on parallel optimization, which relates to the field of motor control, and sequentially comprises the following steps: establishing a permanent magnet synchronous motor mathematical model, performing Euler discretization-based model prediction torque control, and selecting an optimal vector based on a comprehensive optimization mechanism. Compared with the prior art, the optimal vector is selected on the basis of a comprehensive optimization mechanism, so that the control system adaptively switches the priority of multiple targets under high-speed and low-speed working conditions so as to realize multi-dimensional variable global optimization and rapid dynamic coordination, and the control is enabled to meet the performance requirements of preliminary constraint conditions, so that the control efficiency is improved. Ripples of torque and flux linkage are reduced, unstable operation of the motor and extra noise interference are overcome, and the control precision and steady-state performance of a control system are improved.

The application relates to an SGD-PSO-based lens parameter generation method and device and a storage medium, wherein the method comprises the following steps: S1, a basic configuration of a lens in an optical system is acquired, the number of lenses, design requirements and a parameter set are obtained based on the basic configuration of the lens; S2, an optimization target is constructed based on the design requirements, a fitness function is defined according to an optimized objective function, and a particle is defined based on the parameter set, wherein the position of each particle represents a group of values of the parameter set; S3, optimization is performed in an SGD-PSO mode to obtain an optimization result; and S4, the values of the parameters in the parameter set are obtained based on the optimization result. Compared with the prior art, the global information prompt multi-particle parallel optimization algorithm proposed in the application can fully explore the solution space and improve the efficiency of the computing power, and the optimization result, efficiency, stability and diversity are greatly improved through the multi-system independent parallel local optimization algorithm, the heuristic global search algorithm and the gradient-enhanced global algorithm.

The application discloses a two-purpose wrench production full-process intelligent management method and system under an industrial internet of things architecture, and relates to the technical field of industrial internet of things and intelligent manufacturing. The method comprises the following steps: taking the use characteristics of a target two-purpose wrench as a constraint, obtaining single-function production sample data and full-process historical production data; constructing and training a plurality of function performance evaluation bodies based on the data to form an evaluation body set; constructing a bidirectional master-slave optimization channel comprising a first master-slave optimization channel, a second master-slave optimization channel and an information exchange channel according to the evaluation body set; performing bidirectional parallel optimization iteration in combination with the full-process historical production data and the bidirectional master-slave optimization channel, and outputting an optimal process scheme; and finally applying the optimal scheme to a full production environment to realize intelligent management. The application effectively solves the coupling conflict problem of dual-function end production process parameters through a bidirectional optimization architecture, realizes global collaborative optimization, improves product quality and production efficiency, and reduces production cost and the waste product rate.

This invention discloses a parallel optimization system for massive video processing. The system adopts a four-layer integrated parallel and collaborative processing architecture, comprising, from top to bottom: a parallel task layer for video stream access, grouping, splitting, encapsulation, and queue management; a resource abstraction layer for unified hardware modeling, status acquisition, topology construction, and capability assessment; a parallel scheduling layer for task-hardware matching, load balancing, priority scheduling, and dynamic adjustment; and an execution optimization layer for data stream localization, parallel read / write, cache optimization, and zero-copy processing. The parallel task layer, resource abstraction layer, parallel scheduling layer, and execution optimization layer form a complete parallel processing link: task input, resource awareness, accurate scheduling, and optimized execution. This invention implements concurrent rate limiting and smooth access for the input video stream to prevent traffic surges; and sets synchronization points and timing control for parallel tasks to ensure orderly output.

The present application relates to a kind of crack morphology parameter's multiple initial value subinterval nonlinear inversion method, it is applied to petroleum technical field, the multiple initial value subinterval nonlinear inversion method for explaining crack morphology parameter based on crack front fiber strain includes: based on three-dimensional displacement discontinuity method, crack front fiber strain calculation model is established;According to crack parameter and the crack front fiber strain calculation model, predicted strain is calculated;According to the strain residual of measured fiber strain and the predicted strain, nonlinear least square inversion model with parameter boundary constraint is established;The crack parameter includes crack half crack length, crack height, crack net pressure in crack, crack vertical offset;Under coarse grid division, multiple initial values are set in parameter feasible region and are carried out parallel optimization, and first candidate solution is obtained;Again with the crack height of the first candidate solution as center, crack height feasible region is recursively divided into multiple subintervals.

The application discloses a kind of based on machine learning's genome analysis parallel optimization method and system, the method of the present application includes the input BAM file is cut into multiple same size file blocks;For each file block, extract file block characteristics, and input the file block characteristics into the pre-trained machine learning model to obtain the predicted running time of the file block;The predicted running time is in the front part file block is divided into smaller file block;File block is input into HaplotypeCaller in parallel to carry out variation detection;The variation detection result generated by HaplotypeCaller for each file block is merged and output.The present application is aimed at solving the problem of serious calculation tilt and low resource utilization caused by unclear calculation complexity before HaplotypeCaller runs, improving the efficiency of genome analysis, shortening the variation detection duration.

This invention relates to the field of chemical engineering technology, and in particular discloses a parallel optimization method for multivariate alarm values ​​that integrates intelligent identification of operating conditions in chemical plants. The method includes: S1 multi-source data access and preprocessing to achieve unified integration and standardization of data from systems such as DCS and MES; S2 analysis of the preprocessed data based on machine learning to intelligently identify and classify steady-state operating conditions; S3 parallel multivariate correlation analysis, calculation of frequent fluctuation ranges, and effective intervention time for each steady-state operating condition; S4 generating optimized alarm setpoints for different operating conditions based on the calculation results, and displaying a comparison of alarm frequency and optimization effects through a graphical interface; S5 approval, deployment, and application of alarm schemes. This invention combines the advantages of data-driven approaches with the security and interpretability of static alarms, solving the problems of isolated optimization and data distortion, and significantly improving the accuracy and reliability of the alarm system without high-risk dynamic intervention.

A layered hybrid parallel cloud edge end heterogeneous resource collaborative training strategy, research on how to fully utilize the multi-layered hybrid parallel strategy of the search space of the search algorithm of the layered hybrid parallel algorithm, through the dynamic programming algorithm and the resource constraint mechanism to search the possible layered hybrid parallel algorithm, realize the efficient layered hybrid parallel of the cloud edge end collaborative cross-domain scene; research on the runtime cross-domain layered hybrid parallel optimization strategy, through the secondary balanced allocation of the data load and the calculation load in the calculation cluster, adjust the calculation speed between each node, avoid the emergence of slow nodes at runtime. Through the above mechanism, the efficient adaptation of cloud edge heterogeneous computing resources and hybrid parallel strategy is realized, the utilization efficiency of cloud edge heterogeneous computing resources is improved, and the model cross-domain distributed training speed is improved.

The application provides an image data processing method and system based on a lightweight sparse neural network, and relates to the technical field of machine learning, comprising: obtaining image data to be processed; sequentially performing random flipping, random cropping data enhancement and tensor standardization preprocessing on the image data to obtain standard tensor data meeting model input requirements; inputting the standard tensor data into a lightweight sparse neural network model; the model extracts local edge and texture features and global semantic features from the image through multiple sparse convolution layers; the physical features extracted are mapped to class confidence through a full connection layer, and finally a classification result is output through a Softmax function. Through the gradient-guided differential mutation strategy and GPU parallel optimization, the application realizes efficient image processing on resource-limited mobile terminals, embedded devices and edge computing devices, reduces the calculation overhead and memory occupation, and at the same time maintains high-precision classification performance.

This application discloses a method, apparatus, device, medium, and product for multi-layer convolution operator fusion optimization, relating to the field of compiler optimization technology. The method includes: determining the original computation graph of the model to be deployed; determining multiple fusionable operator subgraphs in the original computation graph based on a hardware performance model; optimizing the original computation graph based on the fusionable operator subgraphs to obtain an optimized computation graph; obtaining parallel optimization code for the model to be deployed based on the optimized computation graph and the slice size; and running the parallel optimization code on the target machine to obtain the optimized performance of the model to be deployed. This application improves the performance of the target machine when executing a neural network model by optimizing the original computation graph based on fusionable operator subgraphs.