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

Machine-to-Machine (M2M) communication is crucial in developing Internet ofThings (IoT). As it is well known that cellular networks have been consideredas the primary infrastructure for M2M communications, there are several keyissues to be addressed in order to deploy M2M communications over cellularnetworks. Notably, the rapid growth of M2M traffic dramatically increasesenergy consumption, as well as degrades the performance of existingHuman-to-Human (H2H) traffic. Sustainable operation technology and resourcemanagement are efficacious ways for solving these issues. In this paper, weinvestigate a resource management problem in cellular networks with H2H/M2Mcoexistence. First, considering the energy-constrained nature of machine typecommunication devices (MTCDs), we propose a novel network model enabled bysimultaneous wireless information and power transfer (SWIPT), which empowersMTCDs with the ability to simultaneously perform energy harvesting (EH) andinformation decoding. Given the diverse characteristics of IoT devices, wesubdivide MTCDs into critical and tolerable types, further formulating theresource management problem as an energy efficiency (EE) maximization problemunder divers Quality-of-Service (QoS) constraints. Then, we develop amulti-agent deep reinforcement learning (DRL) based scheme to solve thisproblem. It provides optimal spectrum, transmit power and power splitting (PS)ratio allocation policies, along with efficient model training under designedbehaviour-tracking based state space and common reward function. Finally, weverify that with a reasonable training mechanism, multiple M2M agentssuccessfully work cooperatively in a distributed way, resulting in networkperformance that outperforms other intelligence approaches in terms ofconvergence speed and meeting the EE and QoS requirements.

Multi-Agent Deep Reinforcement Learning Based Resource Management in SWIPT Enabled Cellular Networks with H2H/M2M Co-Existence