OACR²: Online Admission Control and Resource Reservation for 5G Slice Networks With Deep Reinforcement Learning

Network slicing architecture is expected to fulfill network applications with heterogeneous requirements through efficient slice admission control (SAC) policies. Existing SAC approaches entirely rely on current limited observations to make admission decisions, ignoring the potential impact of future demands. The short-sighted behaviors lead to poor service performance and infrastructure providers’ (InPs’) revenue in practice. In this paper, we propose OACR², an online SAC approach based on deep reinforcement learning (DRL) that can exploit predictable future requests to make more precise admission control decisions for the long-term revenue, and reserve proper resources accordingly. Specifically, we design three novel schemes: (i) a requirement predictor based on long short-term memory (LSTM) and a novel input-output way to predict future unforeseen requests, (ii) a DRL admission controller based on the partially observable Markov decision process model to make precise admission decisions without accurate future request information, with the convergence strictly proved, and (iii) a decision defender to guarantee decision reliability. Extensive experiments on real-world traces demonstrate that compared to the No-wait, Wait-queue, and Wait-earliest time approaches, OACR² improves InPs’ revenue and acceptance ratio by up to 40.9% and 16.7%, respectively, without sacrificing online inference time (within 0.9 milliseconds).