In this paper, we describe an algorithmic framework for the optimal operation of transient gas transport networks consisting of a hierarchical MILP formulation together with a sequential linear programming inspired post-processing routine. Its implementation is part of the KOMPASS decision support system, which is currently used in an industrial setting. Real-world gas transport networks are controlled by operating complex pipeline intersection areas, which comprise multiple compressor units, regulators, and valves. In the following, we introduce the concept of network stations to model them. Thereby, we represent the technical capabilities of a station by hand-tailored artificial arcs and add them to network. Furthermore, we choose from a predefined set of flow directions for each network station and time step, which determines where the gas enters and leaves the station. Additionally, we have to select a supported simple state, which consists of two subsets of artificial arcs: Arcs that must and arcs that cannot be used. The goal is to determine a stable control of the network satisfying all supplies and demands. The pipeline intersections, that are represented by the network stations, were initially built centuries ago. Subsequently, due to updates, changes, and extensions, they evolved into highly complex and involved topologies. To extract their basic properties and to model them using computer-readable and optimizable descriptions took several years of effort. To support the dispatchers in controlling the network, we need to compute a continuously updated list of recommended measures. Our motivation for the model presented here is to make fast decisions on important transient global control parameters, i.e., how to route the flow and where to compress the gas. Detailed continuous and discrete technical control measures realizing them, which take all hardware details into account, are determined in a subsequent step. In this paper, we present computational results from the KOMPASS project using detailed real-world data.

在本文中，我们描述了一种用于瞬态气体传输网络优化运行的算法框架，该网络由分层 MILP 公式和顺序线性规划启发的后处理例程组成。它的实施是 KOMPASS 决策支持系统的一部分，该系统目前在工业环境中使用。现实世界的天然气运输网络由操作复杂的管道交叉区域控制，其中包括多个压缩机单元、调节器和阀门。下面，我们引入网络站的概念来对其进行建模。因此，我们通过手工定制的人工弧线来表示站点的技术能力，并将其添加到网络中。此外，我们从一组预定义的每个网络站点的流向和时间步长，决定了气体进入和离开站点的位置。此外，我们必须选择一个受支持的简单状态，由人工弧的两个子集组成：必须使用的弧和不能使用的弧。目标是确定满足所有供应和需求的网络的稳定控制。以网络站为代表的管道交叉口最初是在几个世纪前建造的。随后，由于更新、变化和扩展，它们演变成高度复杂和复杂的拓扑。提取它们的基本属性并使用计算机可读和可优化的描述对它们进行建模需要数年的努力。为了支持调度员控制网络，我们需要计算一个不断更新的推荐措施列表。我们这里介绍的模型的动机是对重要的瞬态全局控制参数做出快速决策，即如何路由流动以及在何处压缩气体。实现它们的详细连续和离散技术控制措施，考虑到所有硬件细节，在后续步骤中确定。在本文中，我们使用详细的真实世界数据展示了 KOMPASS 项目的计算结果。