Dynamic Neighborhood Structures in Parallel Evolution Strategies [report]

Jörn Mehnen, Günter Rudolph, Klaus Weinert, Technische Universität Dortmund, Technische Universität Dortmund
Parallelizing is a straightforward approach to reduce the total computation time of evolutionary algorithms. Finding an appropriate communication network within spatially structured populations for improving convergence speed and convergence probability is a difficult task. A new method that uses a dynamic communication scheme in an evolution strategy will be compared with conventional static and dynamic approaches. The communication structure is based on a socalled diffusion model approach.
more » ... model approach. The links between adjacent individuals are dynamically chosen according to deterministic or probabilistic rules. Due to self-organization effects, efficient and stable communication structures are established that perform robust and fast on a multimodal test function.
doi:10.17877/de290r-15247 fatcat:uumv3ytq5feq5ksr6vhv4wbdrm