An interval-prediction based robust optimization approach for energy-hub operation scheduling considering flexible ramping products

Abstract

The energy-hub (EH) technique provides a new-type conceptual framework for the interaction, coupling, conversion of different forms of energies to achieve the improvement of energy usage efficiency. In this paper, an optimal economic dispatching model for a residential-level EH in the energy market considering the flexible ramping product (FRP) is proposed. As distinct from existing studies, in this work, we assume that the EH not only involves bidding in the energy market but may also get profits by providing the FRP to the grid. The discussed problem is formulated as a two-stage robust optimization (RO) model, wherein the first-stage is dedicated to minimizing the operation cost of the EH by optimizing its bidding strategy (energy and flexible ramping trading quantities) in the DA market, while the second-stage aims to determine the optimal re-dispatch/corrective schedule of the EH (including adjusted output of EH components, bidding and flexible ramping amount) in the RT market to achieve the energy balancing with the least cost, considering the worst-case realization of uncertainties. In practice, since the selection of uncertainty interval has an important impact on the efficacy of the RO solution, we propose an interval prediction-based approach combining the long short-term memory (LSTM) recurrent neural network and bootstrapping technique to determine the uncertainty interval used in our RO formulation. Compared with the conventional empirical-based interval-setting, the proposed prediction-based technique is useful to reduce the conservative level of RO solutions by deep learning the value of historical data and reflecting the real error distribution of point forecast results in its estimation. The effectiveness of the proposed methodology is examined based on a residential EH case, and the obtained results confirm the validity of the proposed approach in actual implementations.