English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multistage stochastic programming provides a modeling framework forsequential decision-making problems that involve uncertainty. One typicallyoverlooked aspect of this methodology is how uncertainty is incorporated intomodeling. Traditionally, statistical forecasting techniques with simple forms,e.g., (first-order) autoregressive time-series models, are used to extractscenarios to be added to optimization models to represent the uncertain future.However, often times, the performance of these forecasting models are notthoroughly assessed. Motivated by the advances in probabilistic forecasting, weincorporate a deep learning-based time-series forecasting method intomultistage stochastic programming framework, and compare it with the caseswhere a traditional forecasting method is employed to model the uncertainty. Weassess the impact of more accurate forecasts on the quality of two commonlyused look-ahead policies, a deterministic one and a two-stage one, in arolling\red{-}horizon framework on a practical problem. Our results illustratethat more accurate forecasts contribute substantially to the model performance,and enable obtaining high-quality solutions even from computationally cheapheuristics. They also show that the probabilistic forecasting capabilities ofdeep learning-based methods can be especially beneficial when used as a(conditional) sampling tool for scenario-based models, and to predict theworst-case scenario for risk-averse models.

On the Impact of Deep Learning-based Time-series Forecasts on Multistage Stochastic Programming Policies