TTDeep: Time-Triggered Scheduling for Real-Time Ethernet via Deep Reinforcement Learning
Hongyu Jia, Yu Jiang, Chunmeng Zhong, Hai Wan, Xibin Zhao
Abstract
Schedule scheme is essential for real-time Ethernet. Due to the inevitable change of network configurations, the solution requires to be incrementally scheduled in a timely manner. Solver-based methods are time-consuming, while handcrafted scheduling heuristics require domain knowledge and professional expertise, and their application scenarios are usually limited. Instead of designing heuristic strategy manually, we propose TTDeep, a deep reinforcement learning schedule framework, to incrementally schedule Time-Triggered (TT) flows and adapt to various topologies. Our novel framework includes 3 key designs: a period layer to capture the periodical transmission nature of TT flows, the graph neural network to extract and represent topology features, and a 3-step selection paradigm to alleviate the huge action search space issue. Comprehensive experiments show that TTDeep can schedule TT flows much faster than solver-based methods and schedule nearly twice more TT flows on average compared to handcrafted heuristics.