Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning
This work addresses the challenge of managing real-time inference workloads for applications like AR/VR in constrained edge networks, but it is incremental as it builds on existing scheduling methods with a reinforcement learning approach.
The paper tackles the problem of scheduling deep neural network inference queries on distributed edge clusters to meet latency and throughput requirements, and shows that their reinforcement learning-based algorithm, ASET, outperforms static policies in simulations using realistic ISP workloads.
Many real-time applications (e.g., Augmented/Virtual Reality, cognitive assistance) rely on Deep Neural Networks (DNNs) to process inference tasks. Edge computing is considered a key infrastructure to deploy such applications, as moving computation close to the data sources enables us to meet stringent latency and throughput requirements. However, the constrained nature of edge networks poses several additional challenges to the management of inference workloads: edge clusters can not provide unlimited processing power to DNN models, and often a trade-off between network and processing time should be considered when it comes to end-to-end delay requirements. In this paper, we focus on the problem of scheduling inference queries on DNN models in edge networks at short timescales (i.e., few milliseconds). By means of simulations, we analyze several policies in the realistic network settings and workloads of a large ISP, highlighting the need for a dynamic scheduling policy that can adapt to network conditions and workloads. We therefore design ASET, a Reinforcement Learning based scheduling algorithm able to adapt its decisions according to the system conditions. Our results show that ASET effectively provides the best performance compared to static policies when scheduling over a distributed pool of edge resources.