2023
Tobias Benecke; Oliver Antons; Sanaz Mostaghim; Julia C. Arlinghaus
A Generalized Circular Supply Chain Problem for Multi-Objective Evolutionary Algorithms Proceedings Article
In: Proceedings of the Companion Conference on Genetic and Evolutionary Computation, pp. 355–358, Association for Computing Machinery, Lisbon, Portugal, 2023, ISBN: 9798400701207.
Abstract | Links | BibTeX | Tags: Benchmarking, Evolutionary algorithms, Multi-objective optimization, Supply chain optimization
@inproceedings{10.1145/3583133.3590742,
title = {A Generalized Circular Supply Chain Problem for Multi-Objective Evolutionary Algorithms},
author = {Tobias Benecke and Oliver Antons and Sanaz Mostaghim and Julia C. Arlinghaus},
url = {https://doi.org/10.1145/3583133.3590742},
doi = {10.1145/3583133.3590742},
isbn = {9798400701207},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Proceedings of the Companion Conference on Genetic and Evolutionary Computation},
pages = {355\textendash358},
publisher = {Association for Computing Machinery},
address = {Lisbon, Portugal},
series = {GECCO '23 Companion},
abstract = {The idea of a circular economy proves promising with the evergrowing need for more sustainable production methods and resource utilization. However, this introduces new challenges compared to the traditional, mostly linear production processes and often leads to a tradeoff between sustainability and costs. In these environments, multi-objective evolutionary algorithms (MOEAs) are a great tool to tackle the increased complexity of supply chains in a circular economy. While MOEAs have been used to optimize circular supply chain models in the past, it was usually done for specific industries and using standard operators. In this paper, we propose a generalized test problem to provide a tool for evaluating MOEAs with respect to a circular supply chain (CSC) problem. In this problem, we try to optimize the product plan as well as the material sourcing at the same time, considering the objectives of maximizing the profit and sustainable resource use.},
keywords = {Benchmarking, Evolutionary algorithms, Multi-objective optimization, Supply chain optimization},
pubstate = {published},
tppubtype = {inproceedings}
}
The idea of a circular economy proves promising with the evergrowing need for more sustainable production methods and resource utilization. However, this introduces new challenges compared to the traditional, mostly linear production processes and often leads to a tradeoff between sustainability and costs. In these environments, multi-objective evolutionary algorithms (MOEAs) are a great tool to tackle the increased complexity of supply chains in a circular economy. While MOEAs have been used to optimize circular supply chain models in the past, it was usually done for specific industries and using standard operators. In this paper, we propose a generalized test problem to provide a tool for evaluating MOEAs with respect to a circular supply chain (CSC) problem. In this problem, we try to optimize the product plan as well as the material sourcing at the same time, considering the objectives of maximizing the profit and sustainable resource use.
Tobias Benecke; Oliver Antons; Sanaz Mostaghim; Julia C. Arlinghaus
A Coevolution Approach for the Multi-objective Circular Supply Chain Problem Proceedings Article
In: 2023 IEEE Conference on Artificial Intelligence (CAI), pp. 222-223, 2023.
Abstract | Links | BibTeX | Tags: Complexity Theory, Costs, Production Planning, Profitability, Supply chain optimization
@inproceedings{10195126,
title = {A Coevolution Approach for the Multi-objective Circular Supply Chain Problem},
author = {Tobias Benecke and Oliver Antons and Sanaz Mostaghim and Julia C. Arlinghaus},
doi = {10.1109/CAI54212.2023.00103},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {2023 IEEE Conference on Artificial Intelligence (CAI)},
pages = {222-223},
abstract = {As a more sustainable resource use is becoming of greater concern, moving towards a more circular economy seems promising. However, compared to the traditional, mostly linear production processes, this introduces new challenges, as reintroducing recycled materials into production also increases supply chain complexity and therefore cost. The circular supply chain (CSC) problem is modeling these challenges to find good tradeoff solutions between profitability and sustainable resource use. The optimization concerns the production planning and material sourcing of a production plant. This is a complex task due to their inherent dependencies. In this paper, we use a cooperative coevolutionary approach to optimize the CSC problem, by decomposing it to resolve the variable dependencies. Besides presenting the algorithm, a proof of concept evaluation is done to show its feasibility.},
keywords = {Complexity Theory, Costs, Production Planning, Profitability, Supply chain optimization},
pubstate = {published},
tppubtype = {inproceedings}
}
As a more sustainable resource use is becoming of greater concern, moving towards a more circular economy seems promising. However, compared to the traditional, mostly linear production processes, this introduces new challenges, as reintroducing recycled materials into production also increases supply chain complexity and therefore cost. The circular supply chain (CSC) problem is modeling these challenges to find good tradeoff solutions between profitability and sustainable resource use. The optimization concerns the production planning and material sourcing of a production plant. This is a complex task due to their inherent dependencies. In this paper, we use a cooperative coevolutionary approach to optimize the CSC problem, by decomposing it to resolve the variable dependencies. Besides presenting the algorithm, a proof of concept evaluation is done to show its feasibility.