An automated model switching framework for efficient entry nomination forecasting in natural gas transmission networks

Abstract As a result of the legislation for gas markets introduced by the European Union in 2005, separate independent companies must conduct the transport and trading of natural gas. The current gas market in Germany, which has a market value of more than 54 billion USD, consists of Transmission System Operators (TSO), network users, and traders. Traders can nominate a certain amount of gas anytime and anywhere in the network. Such unrestricted access for the traders creates a free market while, on the other hand, it increases the uncertainty in the supply management and gas network operations. Some customers’ behaviors may cause abrupt structural changes in the gas flow time series. For this reason, it is challenging for the TSOs to predict the multiple hours-ahead gas nominations accurately. Our study aims to investigate the customers’ behavior in giving the nominations in advance for particular hours and to predict the final gas nominations up to 8 h ahead as precisely as possible. We propose an Automated Model Switching framework (AMS) for an accurate, robust, and efficient multi-step ahead prediction of entry point nominations in gas transmission networks. The results demonstrate that AMS achieves excellent performance, outperforming the best individual state-of-the-art models for the vast majority of the test cases while keeping the calculations as simple as possible.