DRL-Driven Dynamic Resource Allocation for Task-Oriented Semantic Communication
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Semantic communication has been regarded as a promising technology to serve upcoming intelligent applications. However, few studies have addressed the problem of resource allocation in semantic communication networks. Most resource allocation mechanisms act fairly to all original data, ignoring the meaning behind the transmitted bits. In this paper, a dynamic resource allocation scheme for the task-oriented semantic communication network (TOSCN) based on deep reinforcement learning (DRL) is proposed, which allows data with richer semantic information to preferentially occupy limited communication resources. This paper aims to design a deep deterministic policy gradient (DDPG) agent at the micro base station to maximize the long-term transmission efficiency of tasks. Firstly, the relationship between semantic information and task performance is investigated. Subsequently, a novel wireless resource allocation model for TOSCN is proposed by taking the image classification task as an example. Then, a joint optimization problem of the semantic compression ratio, transmit power, and bandwidth of each user is formulated. The agent is trained in an interactive learning environment to obtain a decent trade-off between the amount of data delivered to the receiver and the accuracy of intelligent tasks. Simulation results demonstrate that the proposed scheme achieves significant advantages in relieving communication pressure and improving task performance in resource-constrained wireless networks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Deep Learning Enabled Semantic Communication Systems
Xie, H., Qin, Z., Li, G. Y., & Juang, B.-H. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3071210 · Cited by 1,602 · cited 2×
“In [6], an innovative semantic communication system was developed by introducing Transformer in natural language processing yield and successfully used for text transmission.”
BackgroundMethodEdge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829 · cited 1×
“networks has become an inevitable development trend [1].”
BackgroundA Lite Distributed Semantic Communication System for Internet of Things
Xie, H., & Qin, Z. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036968 · Cited by 497 · cited 1×
“the authors in [9] further investigated an affordable semantic”
Background
Research works printed but not linked: 26
- 10.1109/TCSVT.2019.2895223 · DOI
- 10.23919/JCIN.2020.9200891 · doi:10.23919/jcin.2020.9200891
- 10.1109/TETCI.2018.2883450 · doi:10.1109/tetci.2018.2883450
- 10.1109/TII.2019.2903100 · DOI
- 10.1109/TCOMM.2021.3126626 · DOI
- menon, 2020, Long-tail learning via logit adjustment, arXiv 2007 07314
- 10.1109/JSAC.2021.3064659 · DOI
- 10.1109/MIE.2022.3174331 · DOI
- 10.1016/j.compeleceng.2021.107117 · DOI
- 10.1109/TII.2021.3105489 · DOI
- 10.1109/TII.2021.3097183 · DOI
- 10.1109/JSAC.2021.3126087 · DOI · Paper page
- liu, 2022, Adaptable semantic compression and resource allocation for task-oriented communications, arXiv 2204 08910
- 10.1109/LWC.2022.3170849 · DOI · Paper page
- 10.1109/TWC.2021.3069240 · DOI
- 10.1109/TCOMM.2021.3087624 · DOI
- 10.1007/s11276-021-02632-z · DOI · Paper page
- 10.1109/GLOBECOM48099.2022.10001594 · DOI
- 10.1109/TWC.2020.2981320 · DOI · Paper page
- 10.1109/INFOCOMWKSHPS54753.2022.9797984 · DOI
- 10.1109/TIP.2021.3112316 · DOI
- 10.1109/TCCN.2019.2919300 · DOI · Paper page
- 10.1109/JSAC.2021.3087240 · DOI · Paper page
- 10.1109/TCC.2018.2876242 · doi:10.1109/tcc.2018.2876242
- 10.1109/COMST.2020.2965856 · DOI · Paper page
- 10.1109/MCOM.001.2001239 · DOI · Paper page
Metadata
- Authors
- Zhang, H., Wang, H., Li, Y., Long, K., & Nallanathan, A.
- Venue
- IEEE Transactions on Communications
- Published
- 2023-07
- Volume
- 71
- Issue
- 7
- Pages
- 3992-4004
- ISSN
- 0090-6778 (ISSN-L)
- 1558-0857
- OpenAlex
- W4376455107
- Cited by
- 184
- References
- 6
- FWCI
- 13.49
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- Funders
- National Key Research and Development Program of China (2021YFB2900801)
- National Natural Science Foundation of China (62225103, U22B2003)
- Beijing Natural Science Foundation (L212004)
- Xiaomi Fund of Young Scholar, and China University Industry-University-Research Collaborative Innovation Fund (2021FNA05001)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.