Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform

As the scale of China’s interconnected power grid continues to expand, traditional serial computing methods are no longer sufficient for the rapid analysis and computation of electrical networks with tens of thousands of nodes due to their small scale and low efficiency. To enhance the capability of...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiao Hao, Zongbao Zhang, Zonglin He, Zhengyuan Liu, Zhengdong Tan, Yankan Song
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/17/24/6269
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850049826317664256
author Jiao Hao
Zongbao Zhang
Zonglin He
Zhengyuan Liu
Zhengdong Tan
Yankan Song
author_facet Jiao Hao
Zongbao Zhang
Zonglin He
Zhengyuan Liu
Zhengdong Tan
Yankan Song
author_sort Jiao Hao
collection DOAJ
description As the scale of China’s interconnected power grid continues to expand, traditional serial computing methods are no longer sufficient for the rapid analysis and computation of electrical networks with tens of thousands of nodes due to their small scale and low efficiency. To enhance the capability of online grid analysis, this paper introduces an accelerating batched power flow calculation method based on a heterogeneous CPU-GPU platform. This method, based on the fast decoupled method, combined with the tremendous parallel computing capability of GPUs with the multi-threaded parallel processing of CPUs, efficiently resolves the exceeding bus type conversion issues in GPU-batched power flow calculation and improves the accuracy of the power flow calculations. Then, a binary-based power flow data exchange format was introduced, which utilizes a single binary file for data exchange. This format significantly minimizes I/O time overhead and reduces file size, further enhancing the method’s efficiency. Case studies on real-world power grids demonstrate its high accuracy and reliability. Compared to the traditional single-threaded power flow calculation method, this method dramatically reduces time consumption in batch power flow calculations. It proves the significant advantages of dealing with large-scale power flow calculations.
format Article
id doaj-art-319ea53bcea04287bb6db78d0b8eb4c7
institution DOAJ
issn 1996-1073
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-319ea53bcea04287bb6db78d0b8eb4c72025-08-20T02:53:38ZengMDPI AGEnergies1996-10732024-12-011724626910.3390/en17246269Accelerating Batched Power Flow on Heterogeneous CPU-GPU PlatformJiao Hao0Zongbao Zhang1Zonglin He2Zhengyuan Liu3Zhengdong Tan4Yankan Song5Shenzhen Power Supply Bureau Co., Ltd., Shenzhen 518000, ChinaShenzhen Power Supply Bureau Co., Ltd., Shenzhen 518000, ChinaSichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610000, ChinaSichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610000, ChinaSichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610000, ChinaSichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610000, ChinaAs the scale of China’s interconnected power grid continues to expand, traditional serial computing methods are no longer sufficient for the rapid analysis and computation of electrical networks with tens of thousands of nodes due to their small scale and low efficiency. To enhance the capability of online grid analysis, this paper introduces an accelerating batched power flow calculation method based on a heterogeneous CPU-GPU platform. This method, based on the fast decoupled method, combined with the tremendous parallel computing capability of GPUs with the multi-threaded parallel processing of CPUs, efficiently resolves the exceeding bus type conversion issues in GPU-batched power flow calculation and improves the accuracy of the power flow calculations. Then, a binary-based power flow data exchange format was introduced, which utilizes a single binary file for data exchange. This format significantly minimizes I/O time overhead and reduces file size, further enhancing the method’s efficiency. Case studies on real-world power grids demonstrate its high accuracy and reliability. Compared to the traditional single-threaded power flow calculation method, this method dramatically reduces time consumption in batch power flow calculations. It proves the significant advantages of dealing with large-scale power flow calculations.https://www.mdpi.com/1996-1073/17/24/6269batch power flowheterogeneous CPU-GPUbus type conversionbinary data exchangeGPU acceleration
spellingShingle Jiao Hao
Zongbao Zhang
Zonglin He
Zhengyuan Liu
Zhengdong Tan
Yankan Song
Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform
Energies
batch power flow
heterogeneous CPU-GPU
bus type conversion
binary data exchange
GPU acceleration
title Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform
title_full Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform
title_fullStr Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform
title_full_unstemmed Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform
title_short Accelerating Batched Power Flow on Heterogeneous CPU-GPU Platform
title_sort accelerating batched power flow on heterogeneous cpu gpu platform
topic batch power flow
heterogeneous CPU-GPU
bus type conversion
binary data exchange
GPU acceleration
url https://www.mdpi.com/1996-1073/17/24/6269
work_keys_str_mv AT jiaohao acceleratingbatchedpowerflowonheterogeneouscpugpuplatform
AT zongbaozhang acceleratingbatchedpowerflowonheterogeneouscpugpuplatform
AT zonglinhe acceleratingbatchedpowerflowonheterogeneouscpugpuplatform
AT zhengyuanliu acceleratingbatchedpowerflowonheterogeneouscpugpuplatform
AT zhengdongtan acceleratingbatchedpowerflowonheterogeneouscpugpuplatform
AT yankansong acceleratingbatchedpowerflowonheterogeneouscpugpuplatform