Key Technology Research on End-Side Arithmetic Network Based on Resource Virtualization for Multi-Terminal Systems

Authors

  • Fang Cui China Mobile Group Device Co., Ltd., Beijing 100053, China
  • Mao Ni China Mobile Group Device Co., Ltd., Beijing 100053, China
  • Ting Zhou China Mobile Group Device Co., Ltd., Beijing 100053, China
  • Hengjiang Wang China Mobile Group Device Co., Ltd., Beijing 100053, China

Abstract

As technology continues to advance, intelligent terminal hardware has broken through technical and application barriers and is affecting traditional industries such as healthcare, logistics and energy in a variety of product forms, resulting in the rapid development of multi-terminal collaborative systems. The key technology of the end-side arithmetic network under this systemhas become the key to the improvement of terminal network resource utilisation. This study first optimises the virtual resource scheduling in the multi-terminal system by designing a VM migration algorithm based on the minimum load imbalance, and then proposes a self-coded data compression algorithm, which introduces feature reconstruction and a XGBoost
classification model. Finally, simulation experiments are conducted on the proposed two methods. The outcomes demonstrate that by applying the proposed VM migration algorithm, the I/O, Memory and CPU load imbalance are lower than 0.1, 0.2 and 0.3 respectively, improving the resource utilization. With the proposed data compression algorithm, the classification precision of data compression reaches up to 91% and the running time is reduced by up to 82%, greatly improving the data compression efficiency and providing a new method reference for resource scheduling in end to end computing power networks.

Keywords: Multi-terminal; Resource virtualization; End-side arithmetic networks; Data compression; VM migration

Cite As

F. Cui, M. Ni, T. Zhou, H. Wang, "Key Technology Research on End-Side Arithmetic Network Based
on Resource Virtualization for Multi-Terminal Systems", Engineering Intelligent Systems, vol. 31 no. 5,
pp. 379-387, 2023.








Downloads

Published

2023-09-01

Issue

Vol. 31 No. 5 (2023): International Journal of Engineering Intelligent Systems

Section

Article

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.