High Performance Parallel Research Articles

High-Performance Parallel Computing for Scientific Simulations

One essential strategy for overcoming the difficulties of contemporary scientific simulations is High-Performance Parallel Computing, or HPPC. In order to handle massive information and solve complicated equations, these simulations—which mimic complex phenomena like weather patterns, fluid dynamics, and biological systems—require enormous processing resources. By dividing tasks into smaller components and processing them concurrently, HPPC enables scientists to answer issues more quickly and precisely. Research in several disciplines, including biology, environmental science, engineering, and physics, is greatly advanced by this type of computer.

Highly efficient modeling and optimization of neural fiber responses to electrical stimulation

Peripheral neuromodulation has emerged as a powerful modality for controlling physiological functions and treating a variety of medical conditions including chronic pain and organ dysfunction. The underlying complexity of the nonlinear responses to electrical stimulation make it challenging to design precise and effective neuromodulation protocols. Computational models have thus become indispensable in advancing our understanding and control of neural responses to electrical stimulation. However, existing approaches suffer from computational bottlenecks, rendering them unsuitable for real-time applications, large-scale parameter sweeps, or sophisticated optimization. In this work, we introduce an approach for massively parallel estimation and optimization of neural fiber responses to electrical stimulation using machine learning techniques. By leveraging advances in high-performance computing and parallel programming, we present a surrogate fiber model that generates spatiotemporal responses to a wide variety of cuff-based electrical peripheral nerve stimulation protocols. We used our surrogate fiber model to design stimulation parameters for selective stimulation of pig and human vagus nerves. Our approach yields a several-orders-of-magnitude improvement in computational efficiency while retaining generality and high predictive accuracy, demonstrating its robustness and potential to enhance the design and optimization of peripheral neuromodulation therapies.

A High Performance Parallel Approach to Delay Sum Beamformer in a Homogeneous Multicore Environment

A Cache-Aware Beamformer (CABF) algorithm for the DAS beamformer in a homogeneous multicore processor environment is presented. The context of the proposed algorithm is established by discussing the case for a refined multicore implementation of the beamformer algorithm for a sonar application. The algorithm is designed, implemented, and compared to a regular pthread multicore implementation and a standard OpenMP-based implementation, using arithmetic intensity as the metric. FMA implementations of the algorithms are carried out, and the CABF algorithm is shown to achieve a better arithmetic intensity. A 6000-element array is designed with a simultaneous forming of 200 beams to test the efficacy of cabf in a multicore platform. The results show a 73 % increase in GFLOPS for FMA operations. The performance of the beamformer algorithm for different data sizes is studied, and on average, a 36 % improvement in computational performance is achieved compared to the OpenMP-based implementation.

Design of dual port 9T SRAM cell with parallel processing and high performance computing

Abstract To meet industry requirements of higher transistor count SRAM cells this paper is proposing, a nine-transistor configuration static random access memory (SRAM) cell which is accessible by dual bit line and performing simultaneous read and write operations. The suggested 9T (P9T PS) cell is constructed at 32 nm CMOS and is operating at an operating voltage 0.9 V. To justify the refined performance of proposed design various analysis are carried out that shows the static noise margins (SNM) that occurs while executing the read operation is 0.368 V and hold operation by the cell is 0.364 V, while the write operation has an SNM of 0.422 V. The access time for write and read functions of the cell is found to be 1.2 nS and 4.5 nS respectively. The P9T PS SRAM is compared with other dual-port and single-port 9T SRAM cells is stand out to be pre-eminence in performance in terms of noise immunity, temperature variations, power consumption (static and dynamic both), power delay product (PDP), SNM to PDP and area ratio (SAPR) and electric quality matric. Total leakage power for P9T PS cell is found to be 22.1 nW. The P9T PS bit cell is also found to be power efficient as it is consuming minimal power for all of the operations. Area layout of the P9T (PS) is found to be 22.372 μm2. The results are also supported by the process corner variation analysis for four different corners. LT-spice software is used to carry out all the simulations and analysis.

Tensor approximation of functional differential equations.

Functional differential equations(FDEs) play a fundamental role in many areas of mathematical physics, including fluid dynamics (Hopf characteristic functional equation), quantum field theory (Schwinger-Dyson equations), and statistical physics. Despite their significance, computing solutions to FDEs remains a longstanding challenge in mathematical physics. In this paper we address this challenge by introducing approximation theory and high-performance computational algorithms designed for solving FDEs on tensor manifolds. Our approach involves approximating FDEs using high-dimensional partial differential equations(PDEs), and then solving such high-dimensional PDEs on a low-rank tensor manifold leveraging high-performance (parallel) tensor algorithms. The effectiveness of the proposed approach is demonstrated through its application to the Burgers-Hopf FDE, which governs the characteristic functional of the stochastic solution to the Burgers equationevolving from a random initial state.

Analysis of High-Performance Parallel Computing using TOPSIS Method

High-performance parallel computing involves the simultaneous execution of multiple tasks or processes, orchestrated to achieve improved computational speed and efficiency. This approach leverages the power of parallelism, exploiting both multi-core CPUs and GPUs, distributed computing clusters, and specialized hardware accelerators. The fundamental idea is to divide a task into smaller sub-tasks that can be executed concurrently, thereby reducing processing time and enhancing overall performance. High-performance parallel computing is a transformative approach that enables us to tackle computationally intensive tasks efficiently. This abstract highlight its significance in contemporary computing and sets the stage for further exploration of the intricacies and innovations within this dynamic field. Researchers and practitioners continue to push the boundaries of what is achievable, making high-performance parallel computing a cornerstone of modern computational science and technology. High-performance parallel computing research is of paramount significance due to its transformative impact across diverse fields. It empowers scientists to tackle complex problems that were once computationally intractable, unlocking new frontiers in scientific discovery. It drives innovation in engineering and design, optimizing product development and manufacturing processes across industries. In healthcare, it accelerates genomics research and drug discovery, offering hope for improved medical treatments. Financial institutions rely on it for data analysis and risk assessment, shaping the global economy. Weather forecasting and environmental modelling are enhanced, aiding disaster preparedness and conservation efforts. In the digital age, parallel computing underpins artificial intelligence, enabling advancements in natural language processing and machine learning. Furthermore, it has vital applications in national security, space exploration, and materials science. In essence, high-performance parallel computing research serves as the backbone of technological progress, fostering innovation, efficiency, and problem-solving across a wide spectrum of disciplines, ultimately shaping the future of our world. TOPSIS, this method involves evaluating the geometric distance between each alternative solution and two reference solutions: the positive ideal solution and the negative ideal solution. The underlying principle of TOPSIS assumes that the criteria being assessed are of an ascending nature, where larger values represent better performance. To account for disparate dimensions or scales among the criteria, normalization is often employed within the TOPSIS framework. From the result Scatter- free imaging is got the first rank and object-scatter imaging is having the lowest rank.

Multiple-relaxation-time lattice boltzmann simulation of natural convection of ethylene Glycol -Al[formula omitted]O[formula omitted] power-law Non-newtonian nanofluid in an open enclosure with adiabatic fins

The heat transfer by natural convection of a nanofluid, which is ethylene glycol−Al2O3 has been analyzed in an open cavity numerically using the multiple-relaxation-time - lattice Boltzmann method by the graphics processing unit high-performance parallel computing. The right side of the cavity is open, and different boundary conditions have been applied to all the walls. Besides, one adiabatic fin has been installed on each side of the enclosure’s top and bottom sides. Here, the Prandtl number is fixed at 16.6, and the Rayleigh number changes from 104−106 with the nanoparticle volume fraction from 0%−5% has been used for numerical simulations. Besides, in this work, the power-law index is an important parameter as well, and 0.7, 0.8, 1, 1.2, and 1.4 are the values of this parameter. Results are presented concerning both the average and local Nusselt numbers in the form of streamlines, isotherms, temperature distributions, velocity distributions, heat transfer rate, and entropy production. It is observed when increases, average Nusselt number increases 607.94%, and for this reason, the overall heat transfer rate rises because of buoyancy force. In addition, the average Nusselt number falls by 83.28% when the power-law index rises; as a result, the total heat transfer rate falls because fluid viscosity increases with the power-law index. It is also observed that for shear-thickening fluids, the temperature gradient is higher. On the contrary, the temperature started decreasing with the increase of the power-law index. Additionally, the local Nusselt number value rises as power-law index falls. Moreover, the heat transfer rate increases by 7.08% when volume fraction increases. The intensity of buoyancy force reduces with the increase of volume fraction. Besides, the overall entropy generation rises when the Rayleigh number and the volume fraction increase, but it decreases when the power-law index increases. So, when the Rayleigh number is 106, the power-law index is 0.7, and the volume fraction is 0.00 then the entropy generation is the highest. This current research has many applications for example heat exchangers, electronic cooling equipment, solar heating systems, aerospace applications, medical devices, and entropy generation-related systems.

Integrated Three-Dimensional Airloads and Stresses on Lift-Offset Coaxial Rotors at Extreme Speeds

This paper investigates the three-dimensional (3-D) dynamic stresses on a modern four-bladed hingeless coaxial rotor—inspired by the gross dimensions of the Sikorsky S-97 Raider at extreme flight speeds. The stresses are obtained using integrated 3-D (I3D) aeromechanical analysis—defined as the coupling of 3-D finite element-based structural dynamics with 3-D Reynolds-averaged Navier–Stokes–based fluid dynamics. The coupling was carried out with the University of Maryland/U.S. Army structural dynamic solver X3D and the U.S. Army CREATETM–AV Helios suite of fluid dynamic solvers. The new structural analysis is both enabled and driven by advanced high-performance computing, parallel and scalable solvers, high-order 3-D brick finite elements unified with multibody dynamics, integrated aeromechanics, and a special 3D-to-1D fluid–structure interface that refines the power of the delta-coupling procedure while retaining the advantages of existing computational fluid dynamics mesh motion schemes. The analysis is carried out at 220 knots (μ=0.5)—the cruise speed of the S-97 Raider without reduced tip speed—in order to study the stresses in extreme conditions. At such high speeds, the blade lift is dominated by the complex tip vortex roll-up, and the pitching moments and drag are dominated by the unsteady transonic shocks at the tip. Interesting 3-D dynamic stress patterns are revealed all across the blade that have remained invisible until now since they could neither be predicted nor measured in flight. The key conclusion is that such high-fidelity analysis is now indeed possible and, in fact, necessary to get deeper insights into the dynamics of coaxial rotors at extreme speeds.

Implementing a Hybrid Method for Shack–Hartmann Wavefront Spots Labeling on FPGA

This paper presents a real-time implementation of a hybrid connected component labeling method for processing the Shack–Hartmann wavefront sensor’s images for an adaptive optics (AO) system. The output image of a wavefront sensor is an image of spots. During the sensor’s operation, it can happen that highly distorted wavefronts (WF) may cause the spots to shift outside of their sub-aperture, which may lead to the reduction of the AO system performance. This article explains the benefits of high-performance computing and parallel processing of a field programmable gate array (FPGA). The objective is to calculate the centroids of these spots. A hybrid labeling method was investigated to fulfill this purpose. First, this method was implemented using a forward and backward scan with a respective mask for each scan. Additionally, a relabeling process is applied after labeling each line, and it is carried out in both directions. After labeling, several processing units were implemented in parallel to calculate centroids. Each unit is responsible for calculating the centroid of one label. The system runs in real time with a latency of one frame, which means the output image is a fusion of a current frame and the centroids of the previous frame. Forward and backward labeling requires a large amount of memory, which is the reason for limiting the investigation to forward labeling only. The forward labeling was successfully implemented, and the centroids were detected under minimum spot distortion conditions. This forward labeling implementation also runs in real time with significant latency reduction to calculate the centroids, which leads to minimizing the overall AO system latency, enabling faster computation and correction in addition to reducing the memory usage to 1% when compared to the forward and backward labeling usage of 81% as an advantage for the hardware implementation.

Design and development of a hybrid (mpi+cuda) parallel program for solving the oil displacement problem

In this work, a numerical model of oil displacement was developed using parallel computing technology through the Buckley-Leverett method. Used the hybrid (MPI + CUDA (2 GPU)) high-performance parallel computing technologies. The main goal of this work is by using these two GPU to implement computing processes of distributed data through the MPI, as well as to make a comparative analysis of the computing time and acceleration of parallel algorithms. The MPI, CUDA, hybrid (MPI + CUDA) parallel computing algorithm and the parallel program were realized, and the results were analyzed.

Leveraging Scratchpad Memory in a Hierarchical Architecture for Multicore

This paper proposes a novel architecture for multi-core processors, tailored for high-performance parallel computing. The architecture is founded on the innovative notion that complex problems can be decomposed into three relatively independent sub-problems: data processing, data management, and data communication. It features a grid of small, programmable processing units intricately connected to their three neighbouring units, forming a physically scalable and fractal environment. With flexibility, modularity, and scalability as focal points, this architecture aims to address the anticipated real-time signal processing demands in future telecommunication and multimedia systems. One notable aspect of the proposed architecture is its direct support for object-oriented features at the hardware level. Adopting a hybrid approach with Scratchpad Memory (SPM) combined with Cache in the on-chip memory hierarchy enhances performance and adaptability for sophisticated multi-core applications. The study highlights SPM management and introduces a dynamic data management framework. Unlike traditional SPM allocation methods relying on compiler or profiling knowledge, the proposed approach leverages random sampling and probability theory to predict hot-access data during runtime. This dynamic memory access pattern guides SPM allocation, ensuring optimal utilization of SPM's advantages in access speed and energy consumption, complemented by hardware support from DataUnit. This paper presents a paradigm shift in multi-core processor architecture, offering advanced features to meet the evolving requirements of parallel computing, making it well-suited for future telecommunication and multimedia systems. This paper introduces a revolutionary multicore processor architecture designed for high-performance parallel computing. The foundation of the proposed architecture lies in the innovative concept that complex problems can be decomposed into three relatively independent sub-problems: data processing, data management, and data communication. The architecture features a grid of small, programmable processing units, each intricately connected to its three neighboring units, forming a physically scalable and fractal environment. With a focus on flexibility, modularity, and scalability, this architecture addresses the real-time signal processing demands anticipated in future telecommunication and multimedia systems. One distinctive aspect of the proposed architecture is its direct support for object-oriented features at the hardware level. The on-chip memory hierarchy adopts a hybrid approach with Scratchpad Memory (SPM) combined with Cache, enhancing performance and adaptability for sophisticated multi-core applications. The study emphasizes SPM management and introduces a dynamic data management framework. In contrast to traditional SPM allocation methods relying on compiler or profiling knowledge, the proposed approach leverages random sampling and probability theory to predict hot-access data during runtime. This dynamic memory access pattern guides SPM allocation, ensuring optimal utilization of SPM's advantages in access speed and energy consumption, complemented by hardware support from DataUnit. This paper presents a paradigm shift in multicore processor architecture, offering advanced features to meet the evolving requirements of parallel computing, making it well-suited for future telecommunication and multimedia systems

Numerical modeling of a saxophone and comparison with experimental measurements

Saxophones making has long relied on craftsmanship, associated with an empirical knowledge of their acoustic functioning. The design process is now mainly based on the study of the input impedance, accessible experimentally or computationally. The numerical approaches are currently limited either by the accuracy (analytical models) or by the computation time (numerical resolution of PDEs). The challenge is to propose a numerical method combining both, to access the acoustic pressure and velocity fields in the instrument. Our objective was to develop a high-performance parallel numerical tool based on FEM to model accurately (a few cents on the resonances) the acoustic behavior of the resonator under playing conditions. The computation time was reduced by an order of magnitude compared to the brute force approach, using different modeling strategies specific to wind instruments: First, the modeling of the visco-thermal losses at the walls; then, the reduction of the size of the linear systems and finally, the reuse and model reduction to limit the effect of the multiple resolutions imposed by the wide frequency range of interest. The model is validated by comparison with experimental measurements. An impedance measurement system allowing acquisitions under controlled flow has been developed to reproduce realistic playing conditions.

Mixed Integer Programming based Placement Refinement by RSMT Model with Movable Pins

Placement is a critical step in the physical design for digital application specific integrated circuits (ASICs), as it can directly affect the design qualities such as wirelength and timing. For many domain specific designs, the demands for high performance parallel computing result in repetitive hardware instances, such as the processing elements in the neural network accelerators. As these instances can dominate the area of the designs, the runtime of the complete design’s placement can be traded for optimizing and reusing one instance’s placement to achieve higher quality. Therefore, this work proposes a mixed integer programming (MIP)-based placement refinement algorithm for the repetitive instances. By efficiently modeling the rectilinear steiner tree wirelength, the placement can be precisely refined for better quality. Besides, the MIP formulations for timing-driven placement are proposed. A theoretical proof is then provided to show the correctness of the proposed wirelength model. For the instances in various popular fields, the experiments show that given the placement from the commercial placers, the proposed algorithm can perform further placement refinement to reduce 3.76%/3.64% detailed routing wirelength and 1.68%/2.42% critical path delay under wirelength/timing-driven mode, respectively, and also outperforms the state-of-the-art previous work.

An effective automatic processing engine for improving the multi-GNSS constellation precise orbit prediction

Orbit prediction (OP) recently tends to be a very crucial step for supporting real-time GNSS orbit services due to the dynamic stability of navigation satellite orbits. The OP performance depends on the length of the predicted orbits and the accuracy of precise orbit determination (POD) as basis. Considering this, a new automatic processing engine is established for improving the multiple global navigation satellite systems (multi-GNSS) constellation OP performance. From the architecture-oriented high-performance parallel processing perspective, the multi-node and multi-core computer sources are fully exploited to implement the hourly update of the current multi-GNSS POD. For MEO-type satellites (e.g., Galileo satellites), the accuracy of predicted orbits is improved from 3.8 cm, 6.5 cm, and 12.3 cm to 3.5 cm, 4.3 cm, and 6.3 cm, in the radial, cross, and along directions, respectively, compared to the three-hour POD update. Despite the shortened OP length, the OP performance of regional navigation satellite system (RNSS) satellites is still limited due to their regional observability. The BDS-IGSO and QZSS-IGSO satellitesexhibit radial directional orbital errors of up to 36.9 cm and 28.9 cm, respectively. Therefore, an orbit fitting (OF) processing method with orbit reconstruction is implemented into the processing engine. By utilizing this method, the radial orbital errors for BDS-IGSO and QZSS-IGSO satellites can be reduced to 7.0 cm and 10.4 cm, respectively. The mean real-time positioning errors are thus reduced from 28.3 to 18.4 cm and from 24.4 to 18.2 cm in the horizontal and vertical components, respectively.

Development of software for neuromarketing based on artificial intelligence and data science using high-performance computing and parallel programming technologies

This paper deals with the scientific research in a new area of human activity – neuromarketing. The development of new software for neuromarketing research based on modern methods and tools of artificial intelligence and data science (neural network technologies) using technologies of high-performance computing and parallel programming are considered in this paper. The results of experimental measurements of electrical activity of the consumer's brain based on electroencephalographic signals depending on various types of marketing stimuli are presented in this paper. The quality of the developed software for neuromarketing is evaluated on the basis of various quality metrics.

Crustal heterogeneity effects on coseismic deformation: numerical simulation of the 2008 MW 7.9 Wenchuan earthquake

Coseismic deformation of large earthquakes causes significant property damages and fatalities, which requires quantitative research of multiple disciplines such as geodesy, geological investigation, seismic tomography, and seismic dislocation theory. The finite element method accounts for material heterogeneity and geometric complexity, making it suitable for studying the coseismic deformation of large earthquakes. This paper develops a parallel elastic finite element program that utilizes split nodes and high-performance parallel computing technology on the FELAC software platform to study the coseismic deformation of large earthquakes. We verify the accuracy of the parallel elastic finite element program by comparing its results with the analytical solutions from seismic dislocation theory for four ideal earthquake cases. Finally, we established parallel elastic finite element models to study the coseismic deformation of the 2008 Wenchuan earthquake. The simulation results are consistent with the GPS and InSAR data. Coseismic surface deformation results are significantly influenced by medium regional heterogeneity with different layered structures besides the Longmenshan fault. The finite element program lay the foundation for the inversion of the coseismic fault rupture process based on the heterogeneous medium model and complex geometric model.

A Heterogeneous Parallel Algorithm for Euler-Lagrange Simulations of Liquid in Supersonic Flow

In spite of its prevalent usage for simulating the full-field process of the two-phase flow, the Euler–Lagrange method suffers from a heavy computing burden. Graphics processing units (GPUs), with their massively parallel architecture and high floating-point performance, provide new possibilities for high-efficiency simulation of liquid-jet-related systems. In this paper, a central processing unit/graphics processing unit (CPU/GPU) parallel algorithm based on the Euler–Lagrange scheme is established, in which both the gas and liquid phase are executed on the GPUs. To realize parallel tracking of the Lagrange droplets, a droplet dynamic management method is proposed, and a droplet-locating method is developed to address the cell. Liquid-jet-related simulations are performed on one core of the CPU with a GPU. The numerical results are consistent with the experiment. Compared with a setup using 32 cores of CPUs, considerable speedup is obtained, which is as high as 32.7 though it decreases to 20.2 with increasing droplets.

An efficient framework for matrix-free SpMV computation on GPU for elastoplastic problems

High computational cost in elastoplastic analysis is often handled by the use of high performance parallel computers. However, the presence of both elastic and plastic states leads to the branching issue, which prevents the realization of true parallel performance. The computational efficiency of an elastoplastic analysis using finite element method is largely determined by the performance of repeated solution of linearized system of equations. In this paper, we propose GPU-based matrix-free strategies to compute sparse matrix–vector multiplication (SpMV) in Conjugate Gradient (CG) iterative solver for the acceleration of solution of linear system of equations. Matrix-free solvers never assemble large sparse global tangent matrix and perform the computation directly with small dense elemental matrices, reducing the storage requirement and preventing the use of problematic sparse storage formats. A uniform treatment of elements in elastic and plastic regions is achieved by the proposed single kernel strategy, which prevents branching, avoids redundant computation and provides efficient memory access. In addition, we propose node-based and degrees-of-freedom (DOF)-based parallel strategies for effective implementation of matrix-free SpMV on a GPU. The proposed strategies use single elemental tangent matrix for all elements in elastic region and individual tangent matrices in plastic region. The computational experiments over three large-scale benchmark examples of elastoplasticity reveal that the performance of the node-based and DOF-based parallelization strategies depends on the amount of plasticity in the body. At low plasticity levels, node-based strategy performs best, achieving 3.2× speedup over an existing GPU-based matrix-free SpMV strategy in the literature. For moderate to high amount of plasticity, the DOF-based strategy outperforms every other strategy and obtains speedups of up to 3.5× over the existing SpMV strategy.

Multi-Party Sequential Data Publishing Under Differential Privacy

Given a set of local sequential datasets held by multiple parties, we study the problem of publishing a synthetic dataset that preserves approximate sequentiality information of the integrated dataset while satisfying differential privacy for each local dataset. The existing solutions for publishing differentially private sequential data in the centralized setting mostly adopt tree-based approaches. Such approaches rely on different tree structures that encode sequential data's statistical information. The construction of a tree structure is normally done by recursively splitting nodes whose noisy <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scores</i> (e.g., entropy or count) are larger than a given threshold. However, extending similar ideas to the multi-party setting is challenging. First, the comparison between noisy scores and a given threshold needs to be done in a distributed manner without letting the parties know the noisy scores, while satisfying differential privacy for each local dataset. Second, in the multi-party setting the large number of node splitting decisions incurs prohibitive computation costs. In addressing the above challenges, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DPST</i> , a distributed prediction suffix tree construction solution. In DPST, we first introduce a novel node splitting decision method that calculates the comparison result under encryption with substantially improved efficiency. Then we present a novel batch-based tree construction approach to reduce computation costs. In order to achieve high parallel performance without incurring any extra communication cost, we introduce the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">conjunction</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">slide</i> methods to ensure that each batch contains a stable number of carefully arranged <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">decision tasks</i> . To further reduce communication and computation costs, we propose a prefix-based pre-pruning method to reduce the number of nodes that need to be judged whether to split by an interactive protocol. Extensive experiments on real datasets demonstrate that our DPST solution offers desirable data utility with low computation and communication costs.

A Region-Folding Electromagnetic Transient Simulation Approach for Large-Scale Power Electronics System

This paper proposes a region-folding electromagnetic transient simulation approach for large-scale power electronics systems to boost simulation speed. In the region-folding approach, the loop tear method is proposed to decouple the connections among power electronics blocks, the grouping and pre-calculating method of identical structural blocks is proposed to avoid computing the inverse of matrices repeatedly, and the global simultaneous response procedure is proposed to handle the simultaneous and multiple switching events. The implementation of the proposed approach is combined with high-performance parallelization technology to shorten the simulation time. The Modular Multilevel Converter (MMC)-based High Voltage Direct Current (HVDC) model and DC photovoltaic power station model are simulated respectively to validate the accuracy and efficiency. Simulation results indicate that the proposed approach has the same accuracy as other Electromagnetic Transients (EMT) commercial software with better efficiency.