IEEE Transactions on Vehicular Technology · 2021 · 14 citations · 32 references
ComputingComputer SystemsComputer NetworksDigital CommunicationMobile ComputingCongestion ControlCongestion ManagementDelay ModelingMobile CommunicationQueueing Theory5G Mobile Networks5G NetworksCongestion AvoidanceDelay-based Congestion ControlPrioritization MechanismsPriority ClassificationRandom Access ProtocolsThroughput
Massive Machine-type Communications (mMTC) is one of the principal features of the 5th Generation and beyond (5G+) mobile network services. Due to sparse but synchronous MTC nature, a large number of devices tend to access a base station simultaneously for transmitting data, leading to congestion. To accommodate a large number of simultaneous arrivals in mMTC, efficient congestion control techniques like access class barring (ACB) are incorporated in LTE-A random access. ACB introduces access delay which may not be acceptable in delay-constrained scenarios, such as, eHealth, self-driven vehicles, and smart grid applications. In such scenarios, MTC devices may be forced to drop packets that exceed their delay budget, leading to a decreased system throughput. To this end, in this paper a novel delay-aware priority access classification (DPAC) based ACB is proposed, where the MTC devices having packets with lesser leftover delay budget are given higher priority in ACB. A reinforcement learning (RL) aided framework, called DPAC-RL, is also proposed for online learning of DPAC model parameters. Simulation studies show that the proposed scheme increases successful preamble transmissions by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$75 \%$</tex-math></inline-formula> while ensuring that the access delay is well within the delay budget.
32
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
Florian A. Potra, Stephen J. Wright · Journal of Computational and Applied Mathematics · 2000 · 719 citations