About 20% of the German energy demand is supplied by natural gas. Ad-
ditionally, for about twice the amount Germany serves as a transit country. Thereby, the German network represents a central hub in the European natural gas transport network. The transport infrastructure is operated by so-called transmissions system operators or TSOs. The number one priority of the TSOs is to ensure security of supply. However, the TSOs have no knowledge of the intentions and planned actions of the shippers (traders).
Open Grid Europe (OGE), one of Germany’s largest TSO, operates a high-
pressure transport network of about 12.000 km length. Since flexibility and security of supply is of utmost importance to the German Energy Transition (“Energiewende”) especially with the introduction of peak-load gas power stations, being able to predict in- and out-flow of the network is of great importance.
In this paper we introduce a new hybrid forecast method applied to gas
flows at the boundary nodes of a transport network. The new method employs optimized feature minimization and selection. We use a combination of an FAR, LSTM DNN and mathematical programming to achieve robust high quality forecasts on real world data for different types of network nodes.
Keywords: Gas Forecast, Time series, Hybrid Method, FAR, LSTM, Mathematical Optimisation

Energy storages can be of great value when added to power grids. They introduce the possibility to store and release energy whenever this is favorable. This is particularly relevant, for example, if power supply is volatile (as is the case with renewable energy) and the network is small (so that there are few other nodes that might balance fluctuations in consumption or production). We present models and methods from mathematical optimization for computing an optimized storage schedule for this purpose. We look at alternative optimization objectives, such as smallest possible peak load, low energy costs, or the close approximation of a prescribed load curve. The optimization needs to respect general operational and economic constraints as well as limitations in the use of storage, which are imposed by the chosen storage technology. We therefore introduce alternative approaches for modeling the non-linear properties of energy storages and study their impact on the efficiency of the optimization process. Finally, we present a computational study with batteries as storage devices. We use this to highlight the trade-off between solution quality and computational tractability. A version of the model for the purpose of leveling peaks and instabilities has been implemented into a control system for an office-building smart grid scenario.

As a basis for meaningful simulation and optimization efforts with regard to traffic engineering or energy consumption in telecommunication networks, suitable models are indispensable. This concerns not only realistic network topologies, but also models for the geographical distribution and the temporal dynamics of traffic, as well as the assumptions on network components and technology. This paper derives such a model from the practice of a large national carrier.
Applying the network and traffic model, we demonstrate its use by presenting various optimization cases related to energy-efficient telecommunication. Here, we focus on load-adaptivity by employing sleep modes to the network hardware, where several constraints on the reconfigurability of the network over time are considered.

As a basis for meaningful simulation and optimization efforts with regard to traffic engineering or energy consumption in telecommunication networks, suitable models are indispensable. This concerns not only realistic network topologies but also models for the geographical distribution and the temporal dynamics of traffic, as well as the assumptions on network components and technology. This paper derives such a model from the practice of a large national carrier. Applying the network and traffic model, we demonstrate its use by presenting various optimization cases related to energy-efficient telecommunication. Here, we focus on load adaptivity by employing sleep modes to the network hardware, where several constraints on the reconfigurability of the network over time are considered.