TY - JOUR
T1 - Taking the human out of decomposition-based optimization via artificial intelligence, Part II
T2 - Learning to initialize
AU - Mitrai, Ilias
AU - Daoutidis, Prodromos
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/7
Y1 - 2024/7
N2 - The repeated solution of large-scale optimization problems arises frequently in process systems engineering tasks. Decomposition-based solution methods have been widely used to reduce the corresponding computational time, yet their implementation has multiple steps that are difficult to configure. We propose a machine learning approach to learn the optimal initialization of such algorithms which minimizes the computational time. Active and supervised learning is used to learn a surrogate model that predicts the computational performance for a given initialization. We apply this approach to the initialization of Generalized Benders Decomposition for the solution of mixed-integer model predictive control problems. The surrogate models are used to find the optimal initialization, which corresponds to the number of initial cuts that should be added in the master problem. The results show that the proposed approach can lead to a significant reduction in solution time, and active learning can reduce the data required for learning.
AB - The repeated solution of large-scale optimization problems arises frequently in process systems engineering tasks. Decomposition-based solution methods have been widely used to reduce the corresponding computational time, yet their implementation has multiple steps that are difficult to configure. We propose a machine learning approach to learn the optimal initialization of such algorithms which minimizes the computational time. Active and supervised learning is used to learn a surrogate model that predicts the computational performance for a given initialization. We apply this approach to the initialization of Generalized Benders Decomposition for the solution of mixed-integer model predictive control problems. The surrogate models are used to find the optimal initialization, which corresponds to the number of initial cuts that should be added in the master problem. The results show that the proposed approach can lead to a significant reduction in solution time, and active learning can reduce the data required for learning.
KW - Active learning
KW - Algorithm configuration
KW - Decomposition based solution algorithm
KW - Machine learning
KW - Mixed-integer MPC
KW - Supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85190535134&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85190535134&partnerID=8YFLogxK
U2 - 10.1016/j.compchemeng.2024.108686
DO - 10.1016/j.compchemeng.2024.108686
M3 - Article
AN - SCOPUS:85190535134
SN - 0098-1354
VL - 186
JO - Computers and Chemical Engineering
JF - Computers and Chemical Engineering
M1 - 108686
ER -