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

Mixed integer Model Predictive Control (MPC) problems arise in the operationof systems where discrete and continuous decisions must be taken simultaneouslyto compensate for disturbances. The efficient solution of mixed integer MPCproblems requires the computationally efficient and robust online solution ofmixed integer optimization problems, which are generally difficult to solve. Inthis paper, we propose a machine learning-based branch and check GeneralizedBenders Decomposition algorithm for the efficient solution of such problems. Weuse machine learning to approximate the effect of the complicating variables onthe subproblem by approximating the Benders cuts without solving thesubproblem, therefore, alleviating the need to solve the subproblem multipletimes. The proposed approach is applied to a mixed integer economic MPC casestudy on the operation of chemical processes. We show that the proposedalgorithm always finds feasible solutions to the optimization problem, giventhat the mixed integer MPC problem is feasible, and leads to a significantreduction in solution time (up to 97% or 50x) while incurring small error (inthe order of 1%) compared to the application of standard and acceleratedGeneralized Benders Decomposition.

Computationally efficient solution of mixed integer model predictive control problems via machine learning aided Benders Decomposition