Deep Reinforcement Learning, LSTMs and Pointers for Downlink Scheduling in LTE

Carleton University, Ontario, Canada. July 2021.

Downlink scheduling in the LTE system is an open problem for which several heuristic solutions exist. Recently, there has been an increase in interest in ap-plying machine learning to networking problems, including downlink scheduling. Improvements in Physical Layer capabilities have generated new resource-intensive use cases and continuously modifying existing heuristic solutions could result in the development of systems too complex to maintain over time. We propose a LSTM/Pointer Network-based downlink scheduler which aims to improve upon the current models which utilize feed forward neural networks. Our scheduler flex-ibly handles changing numbers of UEs via the use of a recurrent neural network. We formulate the downlink scheduling problem as a Markov Decision Process that integrates the channel quality indicator and the buffer size of each UE as the observation and solve it using a Deep Reinforcement Learning algorithm. Our experiments demonstrate that our approach results in a scheduler which gener-alised across changing number of UEs and resource blocks and performed within the range of traditional schedulers.