CR-DDPG: cache refreshing for MEC networks with DDPG
In the context of the Industrial Internet of Things (IIoT), multiple access edge computing (MEC) enables the provision of computational resources closer to users. The work presented in this paper explores a common IIoT application scenario wherein autonomous mobile robots (AMR) operate in a MEC-enab...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180159 |
| _version_ | 1826121941617999872 |
|---|---|
| author | Maiti, Ritabrata Madhukumar, A. S. Tan, Ernest Zheng Hui |
| author2 | College of Computing and Data Science |
| author_facet | College of Computing and Data Science Maiti, Ritabrata Madhukumar, A. S. Tan, Ernest Zheng Hui |
| author_sort | Maiti, Ritabrata |
| collection | NTU |
| description | In the context of the Industrial Internet of Things (IIoT), multiple access edge computing (MEC) enables the provision of computational resources closer to users. The work presented in this paper explores a common IIoT application scenario wherein autonomous mobile robots (AMR) operate in a MEC-enabled network and depend on multimedia content stored at the MEC servers over the course of operation. The age of information (AoI) metric is used to measure the freshness of the cached content from the perspective of the AMR. At the same time, the energy cost associated with refreshing the cache files is simultaneously considered as well. This paper delves into achieving an optimal trade-off between minimizing the weighted AoI cost and the energy expended for cache refreshing. We address this problem by introducing a cache refreshing-deep deterministic policy gradient (CR-DDPG) algorithm, a model-free deep reinforcement learning method, to optimize both AoI and energy usage. Various simulation studies are conducted to evaluate the proposed CR-DDPG algorithm, and the results demonstrate that CR-DDPG consistently outperforms its baseline counterparts, rendering it a robust approach for cache-refreshing in dynamic IIoT environments. |
| first_indexed | 2024-10-01T05:40:23Z |
| format | Conference Paper |
| id | ntu-10356/180159 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:40:23Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1801592024-09-23T06:29:48Z CR-DDPG: cache refreshing for MEC networks with DDPG Maiti, Ritabrata Madhukumar, A. S. Tan, Ernest Zheng Hui College of Computing and Data Science School of Computer Science and Engineering IEEE International Conference on Communications (ICC 2024) Engineering Age of information Deep reinforcement learning In the context of the Industrial Internet of Things (IIoT), multiple access edge computing (MEC) enables the provision of computational resources closer to users. The work presented in this paper explores a common IIoT application scenario wherein autonomous mobile robots (AMR) operate in a MEC-enabled network and depend on multimedia content stored at the MEC servers over the course of operation. The age of information (AoI) metric is used to measure the freshness of the cached content from the perspective of the AMR. At the same time, the energy cost associated with refreshing the cache files is simultaneously considered as well. This paper delves into achieving an optimal trade-off between minimizing the weighted AoI cost and the energy expended for cache refreshing. We address this problem by introducing a cache refreshing-deep deterministic policy gradient (CR-DDPG) algorithm, a model-free deep reinforcement learning method, to optimize both AoI and energy usage. Various simulation studies are conducted to evaluate the proposed CR-DDPG algorithm, and the results demonstrate that CR-DDPG consistently outperforms its baseline counterparts, rendering it a robust approach for cache-refreshing in dynamic IIoT environments. Info-communications Media Development Authority (IMDA) National Research Foundation (NRF) This research is supported by the National Research Foundation, Singapore and Infocomm Media Development Authority under its Future Communications Research & Development Programme (FCP-NTU-RG-2022-014), and by the Advanced Remanufacturing and Technology Centre, under the Agency for Science, Technology and Research, Singapore. 2024-09-23T06:29:48Z 2024-09-23T06:29:48Z 2024 Conference Paper Maiti, R., Madhukumar, A. S. & Tan, E. Z. H. (2024). CR-DDPG: cache refreshing for MEC networks with DDPG. IEEE International Conference on Communications (ICC 2024), 262-267. https://dx.doi.org/10.1109/ICC51166.2024.10623065 978-1-7281-9054-9 1938-1883 https://hdl.handle.net/10356/180159 10.1109/ICC51166.2024.10623065 262 267 en FCP-NTU-RG-2022-01 © 2024 IEEE. All rights reserved. |
| spellingShingle | Engineering Age of information Deep reinforcement learning Maiti, Ritabrata Madhukumar, A. S. Tan, Ernest Zheng Hui CR-DDPG: cache refreshing for MEC networks with DDPG |
| title | CR-DDPG: cache refreshing for MEC networks with DDPG |
| title_full | CR-DDPG: cache refreshing for MEC networks with DDPG |
| title_fullStr | CR-DDPG: cache refreshing for MEC networks with DDPG |
| title_full_unstemmed | CR-DDPG: cache refreshing for MEC networks with DDPG |
| title_short | CR-DDPG: cache refreshing for MEC networks with DDPG |
| title_sort | cr ddpg cache refreshing for mec networks with ddpg |
| topic | Engineering Age of information Deep reinforcement learning |
| url | https://hdl.handle.net/10356/180159 |
| work_keys_str_mv | AT maitiritabrata crddpgcacherefreshingformecnetworkswithddpg AT madhukumaras crddpgcacherefreshingformecnetworkswithddpg AT tanernestzhenghui crddpgcacherefreshingformecnetworkswithddpg |