A Reinforcement Learning Approach to Age of Information in Multi-User Networks

Download
2018-01-01
Ceran Arslan, Elif Tuğçe
Gunduz, Deniz
Gyorgy, Andras
Scheduling the transmission of time-sensitive data to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of information (AoI) at the users under a constraint on the average number of transmissions. The source can transmit only to a single user at each time slot, and after each transmission, it receives an instantaneous ACK/NACK feedback from the intended receiver, and decides on when and to which user to transmit the next update. The optimal scheduling policy is first studied under different feedback mechanisms when the channel statistics are known; in particular, the standard automatic repeat request (ARQ) and hybrid ARQ (HARQ) protocols are considered. Then a reinforcement learning (RL) approach is introduced, which does not assume any a priori information on the random processes governing the channel states. Different RL methods are applied and compared through numerical simulations.
29th IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

Suggestions

Average Age of Information with Hybrid ARQ under a Resource Constraint
Ceran Arslan, Elif Tuğçe; Gunduz, Deniz; Gyorgy, Andras (2018-01-01)
Scheduling the transmission of status updates over an error-prone communication channel is studied in order to minimize the long-term average age of information (AoI) at the destination under a constraint on the average number of transmissions at the source node. After each transmission, the source receives an instantaneous ACK/NACK feedback, and decides on the next update without prior knowledge on the success of future transmissions. First, the optimal scheduling policy is studied under different feedback...
Average Age of Information With Hybrid ARQ Under a Resource Constraint
Ceran Arslan, Elif Tuğçe; Gunduz, Deniz; Gyorgy, Andras (2019-03-01)
Scheduling the transmission of status updates over an error-prone communication channel is studied in order to minimize the long-term average age of information at the destination under a constraint on the average number of transmissions at the source node. After each transmission, the source receives an instantaneous ACK/NACK feedback, and decides on the next update without prior knowledge on the success of future transmissions. The optimal scheduling policy is first studied under different feedback mechan...
A simulation study of scheduling algorithms for packet switching networks
Babur, Özgür; Baykal, Buyurman; Department of Electrical and Electronics Engineering (2003)
A scheduling algorithm has the primary role in implementing the quality of service guaranteed to each flow by managing buffer space and selecting which packet to send next with a fair share of network. In this thesis, some scheduling algorithms for packet switching networks are studied. For evaluating their delay, jitter and throughput performances, a discrete event simulator has been developed. It has been seen that fair scheduling provides, fair allocation of bandwidth, lower delay for sources using less ...
A comparative study of evolutionary network design
Kalkan, Sinan; Şehitoğlu, Onur Tolga; Üçoluk, Göktürk; Department of Computer Engineering (2003)
In network design, a communication network is optimized for a given set of parameters like cost, reliability and delay. This study analyzes network design problem using Genetic Algorithms in detail and makes comparison of different approaches and representations. Encoding of a problem is one of the most crucial design choices in Genetic Algorithms. For network design problem, this study compares adjacency matrix representation with list of edges representation. Also, another problem is defining a fair fitne...
Differential network coding in wireless networks Telsiz aǧlarda farksal aǧ kodlamasi
Özdemir, Özgür; Yılmaz, Ali Özgür (2009-10-29)
In this paper a three-terminal communication scenario where two users exchange information by employing differential binary modulation and network coding via a relay is considered. The transmission is divided into three slots in time where the first and second slots are allocated to the transmission of differential encoded data of the users. After demodulation, the relay broadcasts the bit-wise XOR-ed and differential encoded packet to the users in the third slot. The optimum detector and a simplified decis...
Citation Formats
E. T. Ceran Arslan, D. Gunduz, and A. Gyorgy, “A Reinforcement Learning Approach to Age of Information in Multi-User Networks,” presented at the 29th IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Bologna, İtalya, 2018, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/92313.