English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In this paper, a novel experienced deep reinforcement learning (deep-RL)framework is proposed to provide model-free resource allocation for ultrareliable low latency communication (URLLC). The proposed, experienced deep-RLframework can guarantee high end-to-end reliability and low end-to-end latency,under explicit data rate constraints, for each wireless without any models ofor assumptions on the users' traffic. In particular, in order to enable thedeep-RL framework to account for extreme network conditions and operate inhighly reliable systems, a new approach based on generative adversarialnetworks (GANs) is proposed. This GAN approach is used to pre-train the deep-RLframework using a mix of real and synthetic data, thus creating an experienceddeep-RL framework that has been exposed to a broad range of network conditions.Formally, the URLLC resource allocation problem is posed as a powerminimization problem under reliability, latency, and rate constraints. To solvethis problem using experienced deep-RL, first, the rate of each user isdetermined. Then, these rates are mapped to the resource block and powerallocation vectors of the studied wireless system. Finally, the end-to-endreliability and latency of each user are used as feedback to the deep-RLframework. It is then shown that at the fixed-point of the deep-RL algorithm,the reliability and latency of the users are near-optimal. Moreover, for theproposed GAN approach, a theoretical limit for the generator output isanalytically derived. Simulation results show how the proposed approach canachieve near-optimal performance within the rate-reliability-latency region,depending on the network and service requirements. The results also show thatthe proposed experienced deep-RL framework is able to remove the transienttraining time that makes conventional deep-RL methods unsuitable for URLLC.

Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication