Machine learning assisted hyper-heuristics for online combinatorial optimization problems
971
15.4
Microsoft Research335 тыс
Следующее
12.12.22 – 74030:03Популярные
14 дней – 75254:37
Опубликовано 12 декабря 2022, 20:34
2022 Data-driven Optimization Workshop: Machine learning assisted hyper-heuristics for online combinatorial optimization problems
Speaker: Ruibin Bai, The University of Nottingham Ningbo China
In the past decade, considerable advances have been made in the field of computational intelligence and operations research. However, the majority of these optimization approaches have been developed for deterministically formulated problems, the parameters of which are often assumed perfectly predictable prior to problem-solving. In practice, this strong assumption unfortunately contradicts the reality of many real-world problems which are subject to different levels of uncertainties. The solutions derived from these deterministic approaches can rapidly deteriorate during execution due to the over-optimization without explicit consideration of the uncertainties. To address this research gap, two data-driven hyper-heuristic frameworks are investigated. This talk will present the main ideas of the methods and their performance for two combinatorial optimization problems: a real-world container terminal truck routing problem with uncertain service times and the well-known online 2D strip packing problem. The talk shall briefly describe a port digital twin system developed by our team for the purpose of integrated optimization of multiple port operations.
Speaker: Ruibin Bai, The University of Nottingham Ningbo China
In the past decade, considerable advances have been made in the field of computational intelligence and operations research. However, the majority of these optimization approaches have been developed for deterministically formulated problems, the parameters of which are often assumed perfectly predictable prior to problem-solving. In practice, this strong assumption unfortunately contradicts the reality of many real-world problems which are subject to different levels of uncertainties. The solutions derived from these deterministic approaches can rapidly deteriorate during execution due to the over-optimization without explicit consideration of the uncertainties. To address this research gap, two data-driven hyper-heuristic frameworks are investigated. This talk will present the main ideas of the methods and their performance for two combinatorial optimization problems: a real-world container terminal truck routing problem with uncertain service times and the well-known online 2D strip packing problem. The talk shall briefly describe a port digital twin system developed by our team for the purpose of integrated optimization of multiple port operations.
Свежие видео
5 дней – 19617:22
11 дней – 305 51420:13
12 дней – 5 9351:41
12 дней – 432:46
13 дней – 94 23032:15Случайные видео
92 дня – 1 145 1372:09:45
145 дней – 19 71014:37
146 дней – 11 2230:50
13.08.23 – 5 0414:19
20.11.22 – 9 7210:29
18.04.19 – 1 035 42115:28
10 часов – 50 39014:34
4 дня – 40 19516:57
6 дней – 3058:04
6 дней – 3854:23
9 дней – 160 57018:21
