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, we develop a multi-agent reinforcement learning (MARL)framework to obtain online power control policies for a large energy harvesting(EH) multiple access channel, when only causal information about the EH processand wireless channel is available. In the proposed framework, we model theonline power control problem as a discrete-time mean-field game (MFG), andanalytically show that the MFG has a unique stationary solution. Next, weleverage the fictitious play property of the mean-field games, and the deepreinforcement learning technique to learn the stationary solution of the game,in a completely distributed fashion. We analytically show that the proposedprocedure converges to the unique stationary solution of the MFG. This, inturn, ensures that the optimal policies can be learned in a completelydistributed fashion. In order to benchmark the performance of the distributedpolicies, we also develop a deep neural network (DNN) based centralized as wellas distributed online power control schemes. Our simulation results show theefficacy of the proposed power control policies. In particular, the DNN basedcentralized power control policies provide a very good performance for large EHnetworks for which the design of optimal policies is intractable using theconventional methods such as Markov decision processes. Further, performance ofboth the distributed policies is close to the throughput achieved by thecentralized policies.

Distributed Power Control for Large Energy Harvesting Networks: A Multi-Agent Deep Reinforcement Learning Approach