Deep Reinforcement Learning for Network Selection Over Heterogeneous Health Systems

Chkirbene, Zina; Awad, Alaa; Mohamed, Amr; Erbad, Aiman; Guizani, Mohsen

doi:10.1109/tnse.2021.3058037

Cited by 22 publications

(25 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as we discussed in the previous sections, the data rate control issue is typically addressed via controlling other radio resources such as power and spectrum. In addition, the adaptive rate control is typically addressed as a joint optimization with other radio resources, as we will elaborate in the next section, e.g., as in [157], [158].…”

Section: Synthesis and Reflectionsmentioning

confidence: 99%

“…The authors addressed the problem of multi-RATs assignment and continuous power allocation that maximize the network sum rate. [157], in which the authors address the problem of network selection with the aim of optimizing medical data delivery over heterogeneous health systems. In particular, an optimization problem is formulated in which the network selection problem is integrated with adaptive compression to minimize network energy consumption and latency while meeting applications' QoS requirements.…”

Section: ) In Cellular and Homnetsmentioning

confidence: 99%

“…We also observe that DRL methods for cellular and Hom-Nets as well as IoT wireless networks gain more attention than multi-RAT networks, particularly for D2D communications. In addition, there is a lack of research on applications of DRL for emerging IoT applications, such as healthcare systems as investigated recently in [157], which is also a promising field that requires more attention. Furthermore, we observe a lack of research on DRL applications for joint RRAM in satellite networks, which also deserves more in-depth investigation.…”

Section: Synthesis and Reflectionsmentioning

confidence: 99%

“…For example, RRAM in healthsector IoT applications is different from the environmental IoT applications counterparts. Due to the high sensitivity of data in the health-sector applications, extra data pre-processing must be performed, including data compression and encryption [157]. This will directly affect the number of radio resources to be allocated for such applications.…”

Section: G) Context Of Rrammentioning

confidence: 99%

“…f) DRL-Based RRAM with Generative Adversarial Networks (GANs) for RRAM Ensuring the reliability of DRL algorithms is one of the major challenges and objectives in DRL-based RRAM methods. In many real-life scenarios, we may require to deploy DRL models to allocate resources in vital systems requiring ultrareliability, such as IoT healthcare applications [157]. In this context, there are proposals on Generative Adversarial Networks (GANs), which have emerged recently as an effective technique to enhance the reliability of DRL algorithms [195].…”

Section: Future Research Directionsmentioning

confidence: 99%

See 4 more Smart Citations

Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey

Alwarafy¹,

Abdallah²,

Çiftler³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div>Next generation wireless networks are expected to be extremely complex due to their massive heterogeneity in terms of the types of network architectures they incorporate, the types and numbers of smart IoT devices they serve, and the types of emerging applications they support. In such large-scale and heterogeneous networks (HetNets), radio resource allocation and management (RRAM) becomes one of the major challenges encountered during system design and deployment. In this context, emerging Deep Reinforcement Learning (DRL) techniques are expected to be one of the main enabling technologies to address the RRAM in future wireless HetNets. In this paper, we conduct a systematic in-depth, and comprehensive survey of the applications of DRL techniques in RRAM for next generation wireless networks. Towards this, we first overview the existing traditional RRAM methods and identify their limitations that motivate the use of DRL techniques in RRAM. Then, we provide a comprehensive review of the most widely used DRL algorithms to address RRAM problems, including the value- and policy-based algorithms. The advantages, limitations, and use-cases for each algorithm are provided. We then conduct a comprehensive and in-depth literature review and classify existing related works based on both the radio resources they are addressing and the type of wireless networks they are investigating. To this end, we carefully identify the types of DRL algorithms utilized in each related work, the elements of these algorithms, and the main findings of each related work. Finally, we highlight important open challenges and provide insights into several future research directions in the context of DRL-based RRAM. This survey is intentionally designed to guide and stimulate more research endeavors towards building efficient and fine-grained DRL-based RRAM schemes for future wireless networks.</div>

show abstract

Section: Synthesis and Reflectionsmentioning

confidence: 99%

Section: ) In Cellular and Homnetsmentioning

confidence: 99%

Section: Synthesis and Reflectionsmentioning

confidence: 99%

Section: G) Context Of Rrammentioning

confidence: 99%

Section: Future Research Directionsmentioning

confidence: 99%

See 3 more Smart Citations