Hidden order: how adaptation builds complexity
Hidden order: how adaptation builds complexity
Adaptive Retrieval Agents: Internalizing Local Contextand Scaling up to the Web
Machine Learning - Special issue on information retrieval
Hierarchical federations: an architecture for information hiding
Proceedings of the fifteenth workshop on Parallel and distributed simulation
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Trends in Cooperative Distributed Problem Solving
IEEE Transactions on Knowledge and Data Engineering
A Framework to Protect Mobile Agents by Using Reference States
ICDCS '00 Proceedings of the The 20th International Conference on Distributed Computing Systems ( ICDCS 2000)
Efficient and Scalable Pareto Optimization by Evolutionary Local Selection Algorithms
Evolutionary Computation
Decentralized evolutionary agents streamlining logistic network design
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part II
| Hi-index | 0.00 |
There is a trend towards networked and distributed systems, complicating the design process of self-adaptive software. Logistics networks can be seen as a distributed system that have to adapt to requirements of companies and customers in a flexible and fast manner. When constructing and planning logistic networks different aspects of complexity have to be considered: the number of stores, intermediate stores and transport entities that are required at every stage in a supply chain as well as the sufficient size of every store or transport entity. This paper presents an approach that simulates adaptive logistic networks using a multi-agent system (MAS) based on Evolutionary Computation (EC). Our approach uses fully decentralized operators for reproduction like mutation, recombination and selection, regulated by market mechanisms. The novelty of this approach lies in the decentralized bottom-up adaption method for decentralized systems and we use a logistic scenario as an example. Our proposed method is based on a formal model explaining how adaption occurs in the number and strategies of agents and thus of logistic networks. The implementation and experimental results are given to illustrate the expected outcomes.