摘要：Mobile Augmented Reality (MAR) applications demand significant communication, computing and caching resources to support an efficient amalgamation of augmented reality objects (AROs) with the physical world in multiple video view streams. In this paper, the MAR service is decomposed and anchored at different edge cloud locations to optimally explore the scarce edge cloud resources, especially during congestion episodes. In that way, the proposed scheme enables an efficient processing of popular view streams embedded with AROs. More specifically, in this paper, we explicitly utilize the notion of content popularity not only to synthetic objects but also to the video view streams. In this case, popular view streams are cached in a proactive manner, together with preferred/popular AROs, in selected edge caching locations to improve the overall user experience during different mobility events. To achieve that, a joint optimization problem considering mobility, service decomposition, and the balance between service delay and the preference of view streams and embedded AROs is proposed. To tackle the curse of dimensionality of the optimization problem, a nominal long short-term memory (LSTM) neural network is proposed, which is trained offline with optimal solutions and provides high-quality real-time decision making within a gap between 5.6% and 9.8% during inference. Evidence from a wide set of numerical investigations shows that the proposed set of schemes owns around 15% to 38% gains in delay and hence substantially outperforms nominal schemes, which are oblivious to user mobility and the inherent multi-modality and potential decomposition of the MAR services.
