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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The model-driven power allocation (PA) algorithms in the wireless cellularnetworks with interfering multiple-access channel (IMAC) have been investigatedfor decades. Nowadays, the data-driven model-free machine learning-basedapproaches are rapidly developed in this field, and among them the deepreinforcement learning (DRL) is proved to be of great promising potential.Different from supervised learning, the DRL takes advantages of exploration andexploitation to maximize the objective function under certain constraints. Inour paper, we propose a two-step training framework. First, with the off-linelearning in simulated environment, a deep Q network (DQN) is trained with deepQ learning (DQL) algorithm, which is well-designed to be in consistent withthis PA issue. Second, the DQN will be further fine-tuned with real data inon-line training procedure. The simulation results show that the proposed DQNachieves the highest averaged sum-rate, comparing to the ones with present DQLtraining. With different user densities, our DQN outperforms benchmarkalgorithms and thus a good generalization ability is verified.

Power Allocation in Multi-user Cellular Networks With Deep Q Learning Approach