Meta-heuristics Self-Parameterization in a Multi-agent Scheduling System Using Case-Based Reasoning
This paper proposes a novel agent-based approach to Meta-Heuristics self-configuration. Meta-heuristics are algorithms with parameters which need to be set up as efficient as possible in order to unsure its performance. A learning module for self-paramete
- PDF / 417,277 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 90 Downloads / 159 Views
Meta-heuristics Self-Parameterization in a Multi-agent Scheduling System Using Case-Based Reasoning Ivo Pereira, Ana Madureira, and Paulo de Moura Oliveira
Abstract This paper proposes a novel agent-based approach to Meta-Heuristics self-configuration. Meta-heuristics are algorithms with parameters which need to be set up as efficient as possible in order to unsure its performance. A learning module for self-parameterization of Meta-heuristics (MH) in a Multi-Agent System (MAS) for resolution of scheduling problems is proposed in this work. The learning module is based on Case-based Reasoning (CBR) and two different integration approaches are proposed. A computational study is made for comparing the two CBR integration perspectives. Finally, some conclusions are reached and future work outlined.
10.1
Introduction
The Scheduling problem can be defined as “a decision-making process that is used on a regular basis in many manufacturing and services industries. It deals with the allocation of resources to tasks over given time periods and its goal is to optimize one or more objectives” [1], and several approaches have been developed to its resolution. However, many of those approaches are impractical in real manufacturing environments, which are inherently dynamic incorporating complex constraints and where a variety of unexpected disruptions may occur.
I. Pereira (*) • A. Madureira GECAD – Knowledge Engineering and Decision Support Research Center, Institute of Engineering – Polytechnic of Porto (ISEP/IPP), Porto, Portugal e-mail: [email protected]; [email protected] P. de Moura Oliveira Department of Engineering, University of Tra´s-os-Montes e Alto Douro, Vila Real, Portugal e-mail: [email protected] A. Madureira et al. (eds.), Computational Intelligence and Decision Making: Trends and Applications, Intelligent Systems, Control and Automation: Science and Engineering 61, DOI 10.1007/978-94-007-4722-7_10, # Springer Science+Business Media Dordrecht 2013
99
100
I. Pereira et al.
In most real-world environments, scheduling is a progressive reactive process where the presence of real-time information requires continuous reconsideration and review of the pre-established plans. Research on scheduling has not fully addressed this dynamic issue, mostly focusing on the optimization of static scheduling plans [2]. In spite of all research made so far, the scheduling problem is still known to be NP-complete, even in static environments [1]. This fact presents several challenges to conventional algorithms and stimulate researchers to explore new directions. Multi-Agent technology has been considered an important approach for developing industrial distributed systems [3–5] motivating its use in this work. Learning is a crucial component of intelligence, autonomy and pro-activeness which must be a study target of agents and MAS [6]. Panait and Luke [7] described two different approaches of learning in MAS: team learning and concurrent learning. In the first, there is only one apprentice involved, with the objective to learn
Data Loading...
