Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- no (2)
Is part of the Bibliography
- no (2)
Keywords
Institute
As the natural gas market is moving towards short-term planning, accurate and robust short-term forecasts of the demand and supply of natural gas is of fundamental importance for a stable energy supply, a natural gas control schedule, and transport operation on a daily basis. We propose a hybrid forecast model, Functional AutoRegressive and Convolutional Neural Network model, based on state-of-the-art statistical modeling and artificial neural networks. We conduct short-term forecasting of the hourly natural gas flows of 92 distribution nodes in the German high-pressure gas pipeline network, showing that the proposed model provides nice and stable accuracy for different types of nodes. It outperforms all the alternative models, with an improved relative accuracy up to twofold for plant nodes and up to fourfold for municipal nodes. For the border nodes with rather flat gas flows, it has an accuracy that is comparable to the best performing alternative model.
As a result of the legislation for gas markets introduced by the European Union in 2005, separate independent companies have to 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 gas flow time series. For this reason, it is challenging for the TSOs to accurately predict the multiple hours-ahead gas nominations. 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 hours-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.
