41 results about "LU decomposition" patented technology

The invention discloses a matrix calculation unit optimization-based sparse LU decomposition solving method and a related device, and relates to the technical field of numerical algorithm optimization, and the method comprises the steps: calling an improved PRCM algorithm to carry out the reordering of a sparse matrix, improving the local density of data, obtaining a sparse matrix after bandwidth compression, and obtaining a sparse matrix; then converting the sparse matrix into a regular and dense Tile block structure, storing the Tile block structure in a pre-allocated continuous memory space, performing numerical decomposition on the sparse matrix after bandwidth compression by adopting a right view-based LU decomposition algorithm, and accelerating by using a matrix calculation unit in the numerical decomposition process to obtain an LU matrix; therefore, efficient solving of the to-be-solved linear equation can be completed. According to the scheme, the spatial locality of the sparse matrix is fully utilized, the strong computing power of the matrix computing unit is exerted, the computing efficiency is improved while the computing amount is reduced, and the time of sparse LU decomposition in symbol decomposition and numerical decomposition stages is remarkably shortened.

The invention relates to a hierarchical iterative parallel computing method and device for a load flow sparse equation of multiple leading edge surfaces, and the method comprises the steps: distributing different numbers of computing resources for each branch and each node of a Jacobian matrix parallel hierarchical elimination tree according to the structural characteristics of the Jacobian matrix parallel hierarchical elimination tree; according to the allocated computing resources, taking a branch subordinate to a root node of the Jacobian matrix parallel hierarchical elimination tree as a unit, and carrying out sub-matrix computing on nodes in parallel from a lower-layer node to an upper-layer node; storing a Jacobian sub-matrix obtained by sub-matrix calculation, and storing an LU decomposition and contribution sub-matrix of a node dense sub-matrix obtained by LU decomposition of the sub-matrix; and superposing the contribution sub-matrix calculated by the lower-layer node to the corresponding node of the upper layer, and synchronously updating the data in the Jacobian sub-matrix. The power flow equation matrix decomposition efficiency can be improved, and the power flow calculation effectiveness is improved.

The invention discloses a heterogeneous parallel fast direct solution method for accelerating the solution of complex electromagnetic problems, comprising: an MPI process on a CPU side reads a model file and model parameters after three-dimensional geometric modeling of a target; all MPI processes are evenly divided into two groups, all basis functions obtained are divided into M groups, and M×M unit block matrices are generated by using the grouped basis functions to merge and form a block matrix Z; each MPI process obtains basis function information contained in the unit block matrix required by itself according to an acquisition rule related to the MPI process group; all MPI processes complete the LU decomposition process of the block matrix Z in a heterogeneous parallel decomposition method jointly used by a CPU side and a GPU side based on the basis function information obtained by themselves; a current coefficient matrix is ​​solved by back-substitution of a matrix equation group according to the decomposition result of the obtained block matrix Z; and the three-dimensional geometric model of the target is calculated according to the current coefficient matrix to obtain near-field data and far-field data.

The invention discloses a method and system for solving a large-scale ill-conditioned equation set for multi-energy network optimization, and the method comprises the steps: firstly building a multi-time-scale multi-target integrated energy system energy flow optimization model, and solving the multi-time-scale multi-target integrated energy system energy flow optimization model through a Newton-Raphson method; obtaining a large-scale ill-conditioned equation set; then carrying out block dimension reduction on a Jacobian matrix in the large-scale ill-conditioned equation set so as to decompose an iterative equation in the large-scale ill-conditioned equation set into iterative equations of all energy subsystems; and finally, decomposing the jacobian matrix subjected to block dimension reduction by using an incomplete LU decomposition method, and completing independent iterative solution of each energy subsystem by using a stable biorthogonal conjugate gradient method. The method is suitable for rapidly solving the large-scale ill-conditioned equation set when the multi-energy network is optimized, the model is reasonable, the algorithm is correct, economical efficiency and rapidity are met, and the method has engineering application value.

The invention discloses a double-tower system process optimization method based on LU decomposition, and the method comprises the steps: taking the total value of a liquid phase product produced by a double-tower system formed by a depropanizing tower and a debutanizing tower as an optimization target, and constructing an optimization model by combining a constraint equation and a normalization equation; and performing iterative solution on the optimization model based on LU decomposition and a quadratic sequence programming method. According to the method, by judging the correlation of the constraint equation and optimizing the condition number, the influence of ill-conditioned problems can be effectively avoided, and the numerical stability in the solving process is remarkably improved. According to the method, the redundant constraint equation is removed, and the condition number is improved through LU decomposition basis changing, so that unnecessary calculation can be reduced, and the convergence speed of iteration is improved.

The invention discloses an aircraft simulation method, device and equipment based on parallel block sparse matrix incomplete LU decomposition and a medium, and relates to the technical field of simulation, and the method comprises the steps: building a block sparse matrix comprising a plurality of zero sub-blocks and non-zero sub-blocks based on the topological relation of each grid point in an aircraft grid and simulation physical parameters, determining dependency pairs respectively corresponding to a plurality of non-zero sub-blocks from the non-zero sub-blocks, and storing the dependency pairs by adopting a preset data structure; wherein the dependent pair comprises a pair of matched non-zero sub-blocks; respectively distributing the plurality of non-zero sub-blocks to a plurality of GPU thread bundles for parallel processing so as to update the corresponding non-zero sub-blocks based on the updated dependency pairs after the GPU thread bundles complete updating on the dependency pairs corresponding to the corresponding non-zero sub-blocks; and after the plurality of non-zero sub-blocks are updated, updating the block sparse matrix based on the plurality of updated non-zero sub-blocks, and determining an incomplete LU decomposition result according to the updated block sparse matrix so as to perform aircraft simulation.

The invention belongs to the technical field of electromagnetic exploration and numerical simulation. According to the regional decomposition magnetotelluric three-dimensional forward modeling simulation method and system, overlapping DDM is introduced to decompose a large-scale MT problem into a plurality of small sub-domains, so that the calculation complexity is reduced; each small linear system in a sub-domain is solved by using a direct solver, so that the convergence problem of an iterative solver is avoided, an LU decomposition result is repeatedly utilized in a Schwarz iteration process, and the calculation speed is increased; a multi-grid scheme is integrated to accelerate convergence, and a good initial condition is provided through a coarse grid solution, so that the number of iterations is reduced, and the calculation efficiency is further improved; the adaptability of a complex geological structure is enhanced by using an unstructured grid technology, so that the simulation precision is improved; according to the method, the aviation magnetotelluric three-dimensional forward modeling technology which is high in calculation speed and low in memory requirement is developed, and a basis is provided for theoretical research and data three-dimensional inversion of aviation magnetotelluric.

The application belongs to the technical field of power systems, and discloses an EIGD time-delay power system stability analysis method and device, wherein the method comprises the following steps: a linear model of the time-delay power system is established, and the differential equation in the model is converted into an abstract Cauchy problem by using an infinitesimal generator; a group of discrete points is selected for each time-delay interval of the time-delay power system, a discrete function space is established according to the discrete points, and the time-delay variable is discretized to generate a low-order partial infinitesimal generator discretization matrix; displacement and inverse transformation are performed on the discretization matrix to obtain an inverse matrix, and the characteristic value of the system is obtained according to the inverse matrix; the characteristic value is checked by using the Newton method to obtain the accurate characteristic value and the characteristic vector, and the stability of the time-delay power system is analyzed and judged. The method solves the problem of large matrix LU decomposition calculation amount in the existing EIGD time-delay power system characteristic value sparse calculation method based on the DDAE model.

This invention relates to a hierarchical iterative parallel computation method and apparatus for sparse power flow equations with multiple front edges. The method includes: allocating different amounts of computational resources to each branch and node of the parallel hierarchical elimination tree of the Jacobian matrix based on its structural characteristics; performing submatrix computation on nodes in parallel from lower-level nodes to upper-level nodes, taking the branches under the root node of the parallel hierarchical elimination tree as units; storing the Jacobian submatrices obtained from the submatrix computation, and storing the LU decomposition of the node dense submatrices and contribution submatrices obtained from the submatrix LU decomposition; superimposing the contribution submatrices calculated by the lower-level nodes onto the corresponding nodes in the upper level, and synchronously updating the data in the Jacobian submatrices. This invention can accelerate the efficiency of power flow equation matrix decomposition and improve the effectiveness of power flow computation.

The invention discloses a multi-industrial equipment-oriented ELM fault identification method fusing feature attention and manual LU decomposition, and belongs to the technical field of industrial equipment fault diagnosis. The core of the method is that a feature attention mechanism and a manual LU decomposition module are fused: firstly, the feature contribution degree is quantified through a channel attention mechanism, key fault features are automatically focused, weak correlation feature interference is inhibited, and the quality of a hidden layer output matrix is improved; secondly, the manual LU decomposition module realizes autonomous controllability and numerical stability of matrix inverse operation through row principal component selection and regularization optimization, and is separated from the dependence of a third-party math library. According to the method, the accuracy of equipment fault identification is remarkably improved, the omission ratio and the false alarm rate are effectively reduced, memory limitation of edge equipment is overcome, and an efficient and reliable real-time identification scheme is provided for bearing abrasion and gearbox abnormity of a wind power variable pitch system and faults of other industrial equipment such as a machine tool and an industrial motor.

The invention provides a sparse LU decomposition acceleration method for adaptive matrix multiplication based on density perception. The method comprises the steps that multiple sets of sub-matrix blocks corresponding to a target sparse matrix are input into a target random forest model, an optimal matrix multiplication corresponding to each set of sub-matrix blocks is obtained, and the multiple sets of sub-matrix blocks are obtained by grouping a plurality of sub-matrix blocks formed after the target sparse matrix is partitioned; performing LU decomposition on the target sparse matrix based on the optimal matrix multiplication corresponding to each group of sub-matrix blocks to obtain an L matrix and a U matrix corresponding to the target sparse matrix; and performing electronic circuit simulation based on the L matrix and the U matrix corresponding to the target sparse matrix. According to the sparse LU decomposition acceleration method for adaptive matrix multiplication based on density perception, adaptive selection of matrix multiplication can be realized, target sparse matrix LU decomposition can be accelerated, such as a matrix formed by circuit simulation and an electronic circuit simulation speed, and the sparse LU decomposition acceleration method is also suitable for other matrixes with similar structures in other fields.

This invention discloses a method and system for extracting S-parameters of microwave passive devices, comprising: geometrically modeling the microwave passive device and then meshing it to obtain a processed device model; discretizing the processed device model according to basis functions, and performing mode function expansion on the ports of the processed device model to establish a transfinite element matrix equation; performing partial LU decomposition of the system matrix in the transfinite element matrix equation using the multi-wavefront method to obtain the Schur complement matrix of the system matrix and the decomposed system matrix; obtaining the dense S-parameter matrix equation for the microwave passive device based on the Schur complement matrix of the system matrix and the decomposed system matrix; and solving the dense S-parameter matrix equation to obtain the S-parameters of the microwave passive device. This invention effectively reduces the memory usage of matrix calculations and reduces computation time.

The present invention provides a processor for matrix inversion and matrix multiplication, comprising a processing unit (PU) array, a divider array, a memory, and a finite state machine; the processing unit (PU) array is used to perform matrix multiplication and matrix inversion operations; the processing unit (PU) array includes a systolic array. The systolic array in the present invention can implement both matrix multiplication and LU decomposition of matrices and inversion of upper and lower triangular matrices, thereby implementing arbitrary matrix inversion, rather than using two different hardware resources to implement matrix multiplication and matrix inversion separately, thereby significantly improving hardware utilization.

The present invention combines the advantages of fast running speed of spatial domain digital watermarking algorithm and high robustness of frequency domain digital watermarking algorithm, and discloses a spatial domain color digital image blind watermarking method integrating LU decomposition. According to the correlation of the elements of the lower triangular matrix obtained after LU decomposition, the present invention obtains the high correlation elements of the lower triangular matrix obtained after LU decomposition of the image block in the spatial domain, and uses these elements to complete the embedding and blind extraction of the digital watermark in the spatial domain without the need for real LU decomposition. The invention can embed the color image digital watermark into the color host image, and not only has good watermark concealment and strong robustness, but also has good real-time performance, which solves the problem of slow running speed of large-capacity color image digital watermark, and is suitable for occasions of fast and efficient digital media copyright protection.

The present invention implements a high-performance batch parallel LU decomposition method based on GPU for small and medium-sized dense matrices of a simulation system. The method includes: S1, calculating the Jacobian matrix of the model unit of the simulation system at each time step, and taking these matrices as sub-matrices, and splicing them into a large matrix H; S2, dividing the internal blocks of each sub-matrix, and allocating a GPU thread group to each sub-matrix according to the size of the blocks; S3, the GPU thread group sequentially completes the selection of the main element of all columns in each diagonal block, the update of the right block of the row where the diagonal block is located, the exchange of the internal column of the diagonal block with the main element column, and the update of all the block data below and below the column where the diagonal block is located in a diagonal order from the upper left to the lower right, thereby completing the LU decomposition of all sub-matrices in the large matrix H. The present invention can increase the performance in an approximately linear trend as the batch number increases, and can accelerate the solution speed when implicitly solving a model containing a large batch of small ordinary differential equations, and effectively shorten the simulation time.

The invention discloses a linear pre-correction method, device and equipment, a medium and a program product, and the method comprises the steps: obtaining a cross-correlation matrix of a primary function matrix based on the primary function matrix of a current input signal, and judging whether the primary function matrix meets a preset orthogonalization processing condition or not; when the primary function matrix meets the orthogonalization processing condition, performing LU decomposition on the primary function matrix based on a coarse-grained reconfigurable computing architecture to obtain a decomposition matrix; performing orthogonalization processing on the primary function matrix by using the decomposition matrix to obtain a primary function orthogonal matrix; and on the basis of the primary function orthogonal matrix, a correction parameter used for linearization pre-correction is obtained by using a minimum root mean square algorithm. According to the method, the processing efficiency of orthogonalization of the primary function matrix can be improved by utilizing the coarse-grained reconfigurable computing architecture, so that the real-time performance of linear pre-correction in a large-bandwidth or large-scale MIMO scene can be ensured, and the scene limitation is relatively small.

This application discloses a sparse LU decomposition solution method and related apparatus based on matrix computation unit optimization, belonging to the field of numerical algorithm optimization technology. The method includes: reordering the sparse matrix using an improved PRCM algorithm to increase data local density, obtaining a bandwidth-compressed sparse matrix; then converting it into a regular, dense tile block structure and storing it in pre-allocated contiguous memory space; and finally, employing a right-look-based LU decomposition algorithm to numerically decompose the bandwidth-compressed sparse matrix. During the numerical decomposition process, a matrix computation unit is used for acceleration to obtain the LU matrix, which can then be used to efficiently solve the linear equation. This application's solution fully utilizes the spatial locality of the sparse matrix while leveraging the powerful computational capabilities of the matrix computation unit, reducing computational load while improving computational efficiency, significantly reducing the time spent on symbolic and numerical decomposition stages of sparse LU decomposition.

The invention discloses a data processing method and device and related equipment, which can perform LU decomposition of R columns of sub-matrixes on a to-be-decomposed matrix needing to be decomposed in each iteration process in a process of performing LU decomposition calculation on applied to-be-processed data, namely a dense matrix, and calculate a matrix multiplication taking a product of R and sub-matrix dimensions as a dimension. The dimension of matrix multiplication calculation is large, and efficient calculation of matrix multiplication can be achieved. In this way, the dense matrix can be divided into the sub-matrixes with the small granularity, it is guaranteed that the calculation efficiency of matrix multiplication is high on the premise that process loads are balanced, and then the overall efficiency of matrix decomposition calculation is improved.

The application particularly relates to a linear equation set solving method for semiconductor device simulation, which comprises the following steps: determining a target linear equation set, and performing nested partitioning and reordering on a coefficient matrix of the target linear equation set to obtain a transformed coefficient matrix and a corresponding right end vector; based on a preset decomposition precision, the transformed coefficient matrix is decomposed through a selected main element LU decomposition, a forward substitution algorithm and a back substitution algorithm to obtain a current solution vector, and based on a preset working precision, when an initial residual vector does not satisfy a preset solving condition, a modified vector is obtained through a preconditioned GMRES algorithm; based on the preset working precision, the current solution vector and the modified vector, an updated solution vector is obtained as a current solution vector, and a step of calculating a residual vector is re-executed until a latest residual vector after iteration satisfies the preset solving condition, and a final solution is obtained based on the latest current solution vector. Thus, the problems of low solving precision and slow speed in semiconductor device simulation are solved.

The application discloses a ground penetrating radar time domain finite element fast simulation method, system and equipment. The method comprises the following steps: setting geometric parameters and electrical parameters of a two-dimensional complex geoelectric model; constructing a weak form of a two-dimensional electromagnetic wave equation; forming a time domain finite element equation; establishing a linear equation group after central difference time discretization; giving a time step, judging whether the time step meets a CFL stability condition, if yes, directly solving the linear equation group, if not, performing LU decomposition on a coefficient matrix of the linear equation group, and disturbing unstable eigenvalues in the coefficient matrix until absolute values of all eigenvalues of the decomposed coefficient matrix are less than or equal to 1, and generating a reconstruction coefficient matrix; and solving the reconstructed linear equation group, so that the time step breaks through the CFL stability condition. The application can improve the simulation precision of the ground penetrating radar.

The present invention provides a high-quality imaging method for full matrix data based on frequency-domain reverse time migration. The excitation signal, sound velocity distribution, and full matrix data are respectively preprocessed to obtain an excitation sound source matrix, an impedance matrix, and a received sound source matrix. Using the above preprocessing results as inputs, LU decomposition processing is performed on the impedance matrix to solve for the transmitted wave field and the received wave field. Finally, an imaging result is obtained using an imaging condition. This imaging method utilizes the characteristic that the impedance matrix is fixed at the same frequency. Through LU decomposition, the sound pressure fields generated by multiple excitations at the same frequency can be obtained at one time, greatly saving calculation time and improving calculation efficiency. Based on the full wave equation for wave field forward modeling, there is little simplification of wave field propagation, which is suitable for measuring defects in any complex sound velocity distribution and can ensure high quality of the obtained imaging result.

The application discloses a kind of AC / DC hybrid distribution network power flow calculation method and device considering incomplete LU decomposition preconditioning, and relates to the field of smart grid.The method comprises the following steps: establishing active / reactive control equation based on VSC steady-state equation;Based on Kirchhoff's current law, establish AC / DC node power imbalance equation;Taylor expansion is carried out on the above equation, and high-order terms are ignored, to obtain linearized unified power flow equation set and matrix form Jacobian matrix;Incomplete LU decomposition preconditioning is carried out on Jacobian matrix, and stable double-conjugate gradient method is used to solve, to obtain power flow solution.The application establishes unified linearized power flow model, combines incomplete LU decomposition preconditioning and stable double-conjugate gradient method, effectively reduces the sensitivity to initial value, improves the robustness and convergence speed of complex AC / DC hybrid system power flow calculation.

The present application belongs to the technical field of sparse matrix decomposition, and relates to a block method of performance-aware block sparse LU decomposition for a GPU platform, comprising the following steps: S1, constructing a performance function of a GPU computing kernel based on statistical data; S2, based on the performance function, designing a decision method for deciding whether to block a sparse matrix at a specified position; and S3, decomposing the overall block problem of a large-scale sparse matrix into multiple sub-problems decided in sequence, solving each sub-problem one by one based on a greedy heuristic strategy and using the decision method, and obtaining a final specific block scheme. Compared with existing methods, the method of the present application is more excellent in performance in the numerical decomposition stage, and is not only suitable for a heterogeneous platform of multi-core CPU and GPU, but also suitable for a pure CPU architecture.

The application provides a method for solving dynamic voltage drop of a chip-package based on LU decomposition combined with an SMW formula. The chip-package power supply network is regarded as a composite system connected by an interconnection node Pad between a package part and a plurality of chip sub-networks. A chip-package partition solving strategy is introduced. According to the chip and package characteristics, a large-scale sparse matrix of the composite system is disassembled into a structural model with a plurality of diagonal sub-blocks, so as to convert the chip-package power supply network equation into a block structure, and avoid the inefficient redundancy of full matrix repeated decomposition by focusing on necessary coupling calculation. Meanwhile, the SMW formula is used for low-rank incremental updating of the package network influence, so as to quickly update the influence introduced by the package and quickly correct the solution vector. The calculation task is split into a plurality of sub-problems for synchronous execution, so that the plurality of sub-blocks are solved synchronously. The application can provide a high-precision and high-efficiency solution for dynamic voltage drop analysis of a large-scale chip package power supply network.

The present invention provides a method and a related device for calculating the solution time of a node voltage equation in an electromagnetic transient simulation. The method determines the number of non-zero elements and the number of zero elements in each column of an equivalent conductance matrix of the node voltage equation in the electromagnetic transient simulation; solves the element substitution time of the equivalent conductance matrix based on the number of non-zero elements in each column of the equivalent conductance matrix; solves the element solution time of the equivalent conductance matrix and the first matrix solution time of the equivalent conductance matrix after substitution; solves the second matrix solution time based on LU decomposition of the equivalent conductance matrix of the node voltage equation in the electromagnetic transient simulation; solves the order threshold of the equivalent conductance matrix based on the first matrix solution time and the second matrix solution time, selects a solution method with a shorter matrix solution time based on the order of the equivalent conductance matrix, and obtains the corresponding solution time. The present invention provides the matrix solution time of the equivalent conductivity matrix of the node voltage equation in electromagnetic transient simulation and the solution time of the equivalent conductivity matrix based on LU decomposition, which can quantify the computational performance of the node voltage equation and theoretically quantify the performance advantages and disadvantages of different solution methods.

The invention discloses a reconfigurable matrix operation circuit and system, and belongs to the field of high-performance computing hardware accelerators, and the circuit comprises a first operation input end which is used for receiving matrix data; the first operation output end is used for outputting a matrix operation result; the system comprises M cascaded processing units, an independent operation part, a result collection unit and a module top layer control logic, the first processing unit in the M processing units is connected with a first operation input end, the Mth processing unit is connected with a first operation output end, and each processing unit comprises an internal state machine and an operation core; the module top layer control logic is used for setting an internal state machine in the processing unit to realize Cholesky decomposition, LU decomposition, QR decomposition, lower triangular matrix inversion and matrix transposition multiplication operation of a matrix; the result collection unit is used for collecting operation results; and the independent operation component is used for realizing rooting operation and division operation. By means of the reconfigurable matrix operation circuit, hardware multiplexing is achieved, and resources are saved.

A calculation method for the solving time of a node voltage equation in electromagnetic transient simulation, and a related apparatus. The method comprises: for an equivalent conductance matrix of a node voltage equation in electromagnetic transient simulation, determining the number of non-zero elements and the number of zero elements in each column of the equivalent conductance matrix; on the basis of the number of non-zero elements in each column of the equivalent conductance matrix, calculating the element permutation time of the equivalent conductance matrix; for the equivalent conductance matrix which has been subjected to permutation, calculating the element solving time of the equivalent conductance matrix and a first matrix solving time; for the equivalent conductance matrix of the node voltage equation in electromagnetic transient simulation, calculating a second matrix solving time based on LU decomposition; and on the basis of the first matrix solving time and the second matrix solving time, calculating an order threshold value of the equivalent conductance matrix, and on the basis of the order of the equivalent conductance matrix, selecting a solving method involving less matrix solving time, and obtaining a corresponding solving time. The present invention provides the matrix solving time of the equivalent conductance matrix of the node voltage equation in electromagnetic transient simulation, and an equivalent conductance matrix solving time based on LU decomposition, which can quantify the computational performance of the node voltage equation and theoretically quantify the performance advantages and disadvantages of different solving methods.

The application provides a kind of casting billet online thermal state tracking method, comprising the following steps: according to the rule of block division, the asymmetric profiled blank is divided into area block, and the casting billet center area block and the casting billet surface area block are obtained respectively;The structured coarse grid division is carried out to the casting billet center area block, and the structured fine grid division is carried out to the casting billet surface area block, to obtain a plurality of structured grids, and the grid nodes of the structured grid are indexed and described, and the grid data of each structured block and the index are stored correspondingly;The heat transfer equation coefficient matrix and the solidification latent heat release source term of the grid unit of each structured block are calculated;The temperature field of the grid unit in the structured block is calculated by coupling the incomplete matrix LU decomposition and SIP algorithm in turn. By using the application, the problems of the prior art, such as unsuitable for asymmetric profiled blank and slab dual-purpose casting machine, reduced system reliability and time step limitation, can be solved.

The invention discloses a GPU acceleration LU algorithm of a CSC format sparse matrix in a power system. The GPU acceleration LU algorithm comprises the following steps: compressing and storing an input sparse matrix into a CSC format according to a column priority; based on the stored CSC format, realizing an LU decomposition numerical algorithm suitable for a sparse matrix; parallel parts in the LU decomposition numerical algorithm are realized on a GPU, and parallel design is carried out; and timing the solution. According to the method, by changing the matrix format, in the actual high-dimensional power grid matrix, the parallel LU decomposition efficiency of the power sparse matrix is improved, and the problem that time consumption is large in time domain simulation of power grid nodes in a power system is solved.

The invention discloses a hybrid multi-layer preprocessing method and system for an ill-conditioned power flow system, and mainly relates to the technical field of data calculation of a power system. Comprising the following steps: obtaining an original Jacobian matrix J based on a power flow calculation method of a power system, and executing l1 norm scaling on the original Jacobian matrix to obtain a scaled matrix; performing approximate minimum sorting on the scaling matrix to obtain a rearranged matrix; performing incomplete LU decomposition on the rearrangement matrix to obtain a decomposition matrix; and performing hybrid precondition device integration according to the scaling matrix, the rearrangement matrix and the decomposition matrix. The method has the beneficial effects that the risk of convergence failure is reduced, the decomposition efficiency is improved, and meanwhile, the precision and the calculation efficiency are balanced.