Transformer meets wcDTW to improve real-time battery bids: A new approach to scenario selection

arXiv:2404.01646v1 Announce Type: new
Abstract: Stochastic battery bidding in real-time energy markets is a nuanced process, with its efficacy depending on the accuracy of forecasts and the representative scenarios chosen for optimization. In this paper, we introduce a pioneering methodology that amalgamates Transformer-based forecasting with weighted constrained Dynamic Time Warping (wcDTW) to refine scenario selection. Our approach harnesses the predictive capabilities of Transformers to foresee Energy prices, while wcDTW ensures the selection of pertinent historical scenarios by maintaining the coherence …

abstract accuracy arxiv battery bidding cs.cy cs.lg energy forecasting markets methodology optimization paper process real-time stochastic transformer type