A Queueing Analysis of Multi-model Multi-input Machine Learning Systems

被引:5
作者
Makino, Yuta [1 ]
Phung-Duc, Tuan [1 ]
Machida, Fumio [2 ]
机构
[1] Univ Tsukuba, Dept Policy & Planning Sci, Ibaraki, Japan
[2] Univ Tsukuba, Dept Comp Sci, Ibaraki, Japan
来源
51ST ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS (DSN-W 2021) | 2021年
关键词
machine learning; throughput; performance; queueing model; redundant architecture;
D O I
10.1109/DSN-W52860.2021.00033
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
A multi-model multi-input machine learning system (MLS) is an architectural approach to improve the reliability of the MLS output by using multiple models and multiple sensor inputs. While the errors in MLS output can be reduced by redundancy with diversity, the performance overhead/gain caused by the employed architecture may also be concerned in safety-critical applications such as a self-driving car. In this paper, we proposed queueing models for analyzing a multi-model multi-input MLS performance in two architectures, namely a parallel MLS and a shared MLS. The parallel MLS architecture runs two different machine learning models in parallel, while the shared MLS architecture runs a single machine learning model but uses two different sensor inputs. We model the behavior of the parallel MLS by a quasi-birth-death process. On the other hand, we model dynamics of the shared MLS as a continuous-time Markov chain of GUM/1 type. The numerical experiments on the proposed models show that the parallel MLS generally achieves better throughput performance than the shared MLS under the same parameter settings. We also show that the throughput performance of the shared MLS can be improved when the input data arrival rates are sufficiently high.
引用
收藏
页码:141 / 149
页数:9
相关论文
共 50 条
[31]   An Approximate Queueing Model for Multi-Rate Multi-User MIMO Systems [J].
Bellalta, Boris ;
Daza, Vanesa ;
Oliver, Miquel .
IEEE COMMUNICATIONS LETTERS, 2011, 15 (04) :392-394
[32]   Multi-Input Deep Learning Models for Weight Forecasting of Pigs Using Depth Images [J].
Ranjan, Pranjal ;
Ha, Dong Sam ;
Morota, Gota ;
Shin, Sook .
2024 IEEE 36TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2024, :1048-1055
[33]   A multi-model ensemble approach for reservoir dissolved oxygen forecasting based on feature screening and machine learning [J].
Zhang, Peng ;
Liu, Xinyang ;
Dai, Huancheng ;
Shi, Chengchun ;
Xie, Rongrong ;
Song, Gangfu ;
Tang, Lei .
ECOLOGICAL INDICATORS, 2024, 166
[34]   Enhancing robustness in machine-learning-accelerated molecular dynamics: A multi-model nonparametric probabilistic approach [J].
Quek, Ariana ;
Ouyang, Niuchang ;
Lin, Hung-Min ;
Delaire, Olivier ;
Guilleminot, Johann .
MECHANICS OF MATERIALS, 2025, 202
[35]   A multi-model machine learning framework for breast cancer risk stratification using clinical and imaging data [J].
Miao, Lu ;
Li, Zidong ;
Gao, Jinnan .
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2025, 33 (02) :360-375
[36]   One Step Ahead Energy Load Forecasting: A Multi-model approach utilizing Machine and Deep Learning [J].
Mystakidis, Aristeidis ;
Ntozi, Evangelia ;
Afentoulis, Konstantinos ;
Koukaras, Paraskevas ;
Giannopoulos, Georgios ;
Bezas, Napoleon ;
Gkaidatzis, Paschalis A. ;
Ioannidis, Dimosthenis ;
Tjortjis, Christos ;
Tzovaras, Dimitrios .
2022 57TH INTERNATIONAL UNIVERSITIES POWER ENGINEERING CONFERENCE (UPEC 2022): BIG DATA AND SMART GRIDS, 2022,
[37]   Scheduling for Multi-User Multi-Input Multi-Output Wireless Networks with Priorities and Deadlines [J].
Raviv, Li-on ;
Leshem, Amir .
FUTURE INTERNET, 2019, 11 (08)
[38]   Hybrid multi-model ensemble learning for reconstructing gridded runoff of Europe for 500 years [J].
Singh, Ujjwal ;
Maca, Petr ;
Hanel, Martin ;
Markonis, Yannis ;
Nidamanuri, Rama Rao ;
Nasreen, Sadaf ;
Blocher, Johanna Ruth ;
Strnad, Filip ;
Vorel, Jiri ;
Riha, Lubomir ;
Raghubanshi, Akhilesh Singh .
INFORMATION FUSION, 2023, 97
[39]   Multi-model ensemble framework for analysis of psychopathic traits in heinous crime convicts [J].
Singh, Aman ;
Mohapatra, Subrajeet .
JOURNAL OF COMPUTATIONAL SOCIAL SCIENCE, 2025, 8 (03)
[40]   Multi-Perspective Machine Learning (MPML) A Machine Learning Model for Multi-faceted Learning problems. [J].
Miller, Sean ;
Busby-Earle, Curtis .
PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI), 2017, :363-368