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

Cellular-based networks are expected to offer connectivity for massiveInternet of Things (mIoT) systems. However, their Random Access CHannel (RACH)procedure suffers from unreliability, due to the collision from thesimultaneous massive access. Despite that this collision problem has beentreated in existing RACH schemes, these schemes usually organize IoT devices'transmission and re-transmission along with fixed parameters, thus can hardlyadapt to time-varying traffic patterns. Without adaptation, the RACH procedureeasily suffers from high access delay, high energy consumption, or even accessunavailability. With the goal of improving the RACH procedure, this papertargets to optimize the RACH procedure in real-time by maximizing a long-termhybrid multi-objective function, which consists of the number of access successdevices, the average energy consumption, and the average access delay. To doso, we first optimize the long-term objective in the number of access successdevices by using Deep Reinforcement Learning (DRL) algorithms for differentRACH schemes, including Access Class Barring (ACB), Back-Off (BO), andDistributed Queuing (DQ). The converging capability and efficiency of differentDRL algorithms including Policy Gradient (PG), Actor-Critic (AC), DeepQ-Network (DQN), and Deep Deterministic Policy Gradients (DDPG) are compared.Inspired by the results from this comparison, a decoupled learning strategy isdeveloped to jointly and dynamically adapt the access control factors of thosethree access schemes. This decoupled strategy first leverage a Recurrent NeuralNetwork (RNN) model to predict the real-time traffic values of the networkenvironment, and then uses multiple DRL agents to cooperatively configureparameters of each RACH scheme.

A Decoupled Learning Strategy for Massive Access Optimization in Cellular IoT Networks