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.

Time-triggered (TT) communication has long been studied in various industrial domains. The most challenging task of TT communication is to find a feasible schedule table. Network changes are inevitable due to the topology dynamics, varying data transmission requirements, etc. Once changes occur, the schedule table needs to be re-calculated in a timely manner. Solver-based methods and heuristic-based methods were proposed to solve this problem. However, solver-based methods employ integer linear programming (ILP) or satisfiability modulo theories (SMT) which have high computational complexity. On the other hand, heuristic-based methods are fast, but they need to be handcrafted based on the application characteristics. Thus, these methods are not general enough to work in complex scenarios especially in large networks.In this paper we propose DRLS – Deep Reinforcement Learning based TT Scheduling method. DRLS first trains an application or network specific scheduling agent offline. Then, the agent can be used for online scheduling of TT flows. However, off-the-shelf reinforcement learning techniques cannot handle the TT scheduling problem with typical complexity and scale. DRLS provides novel solutions to this challenge, including three key innovations: new representations for TT network adapted to various topologies, proper deep neural network (DNN) structures to capture network characteristics, and scalable reinforcement learning (RL) models to handle online TT scheduling. Comprehensive experiments have been conducted to compare the performance of DRLS and other methods (heuristics-based methods such as HLS, LS, HLD + LD, LS + LD, and ILP-based method). The results show that DRLS can not only adapt to specific network topologies, but also have better performance: runs much faster than ILP solver-based methods, and schedules about 23.9% more flows than traditional handcrafted heuristic-based methods.

Very Fast Decision Tree (VFDT) is one of the most widely used online decision tree induction algorithms, and it provides high classification accuracy with theoretical guarantees. In VFDT, the split-attempt operation is essential for leaf-split. It is computation-intensive since it computes the heuristic measure of all attributes of a leaf. To reduce split-attempts, VFDT tries to split at constant intervals (for example, every 200 examples). However, this mechanism introduces split-delay for split can only happen at fixed intervals, which slows down the growth of VFDT and finally lowers accuracy. To address this problem, we first devise an online incremental algorithm that computes the heuristic measure of an attribute with a much lower computational cost. Then a subset of attributes is carefully selected to find a potential split timing using this algorithm. A split-attempt will be carried out once the timing is verified. By the whole process, computational cost and split-delay are lowered significantly. Comprehensive experiments are conducted using multiple synthetic and real datasets. Compared with state-of-the-art algorithms, our method reduces split-attempts by about 5 to 10 times on average with much lower split-delay, which makes our algorithm run faster and more accurate.

Nowadays in order to stay competitive, business needs to collaborate with each other to offer value added services. Collaborative business process development require loose coupling between individual business processes so that they can interoperate freely across the Internet and that the collaboration can be established in a highly dynamic fashion and on-demand basis. Service oriented computing (SOC) is able to meet such request by establishing business collaboration (BC) to utilize business processes (BPs) crossing organizational boundaries. BP is organizational based, which is about one organization composing services; while BC is choreographically based, which is about cooperation between organizations by linking their BPs. A successful BC development needs to follow the chorographical requirement to ensure the consistency among individual BPs across organizations. It also needs to meet the organizational requirements to ensure each organization's BP performs according to its business rules and conforms to what is specified from collaboration point of view. The current Web services (WS) technologies have provided specifications and tools for BC development. However methodologies, and real case study and experience report in BC development is lacking in the literature. In this paper a business collaboration framework (BCF) is proposed which breaks the BC requirements into 3 layers, each of which models different aspect in the BC development. Practical experience and issues on how to use the BCF is presented and discussed in a case studyeveloping BC in capital marketplace (CM), a project sponsored by the Capital Markets Cooperative Research Centre (CMCRC)