Energy redistribution in autonomous hybridization of agent-based computing

Abstract

Evolutionary multi-agent systems (EMAS) are very good at dealing with difficult, multi-dimensional problems. Currently, research is underway to improve this algorithm, giving even more freedom to agents not only in solving the problem but also in making decisions on the behavior of the algorithm. One way is to hybridize this algorithm with other existing algorithms creating Hybrid Evolutionary Multi Agent-System (HEMAS). Unfortunately, such connections generate problems in the form of an unbalanced energy level of agents who have made the decision to use such an improvement. One of the solutions is the mechanism of redistributing the agents' energy in the form of an operator. The article presents several proposals of redistribution operators along with numerous experimental results.

Applying autonomous hybrid agent-based computing to difficult optimization problems

“…In order to maintain the homogeneity of the whole algorithm, dedicated methods for redistributing the energy (a resource that controlled EMAS) were applied after returning from the hybrid step [20].…”

“…Several methods of the energy redistribution were invented; namely, proportional, ranking, and tournament (following well-known selection methods [6]). Based on the results that are discussed in [20],…”