Assessment of the “Evaluation” function in the simulated evolution algorithm

Simulated Evolution is a stochastic evolutionary search strategy. The algorithm repeatedly executes evaluation, selection, and allocation steps in a sequence, until certain stopping conditions are met. The evaluation step assesses the quality of each individual element of a solution with respect to a single or multiple attributes. The outcome of this step, combined with the results of the selection step, play an important role during the allocation step, where the existing solution is perturbed to generate a new solution. This paper attempts to study the effect of the evaluation step on the quality of the solutions produced by the allocation step. Results suggest that, in general, the Unified And-Or (UAO) operator based evaluation scheme performs significantly well compared to other evaluation approaches.

[1]  Prithviraj Banerjee,et al.  ESp: Placement by simulated evolution , 1989, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[2]  Prithviraj Banerjee,et al.  Empirical and theoretical studies of the simulated evolution method applied to standard cell placement , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[3]  Prithviraj Banerjee,et al.  Optimization by simulated evolution with applications to standard cell placement , 1991, DAC '90.

[4]  Youn-Long Lin,et al.  TRACER-fpga: a router for RAM-based FPGA's , 1995, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[5]  Sathyanarayan S. Rao,et al.  Design of discrete coefficient FIR filters by simulated evolution , 1996, IEEE Signal Processing Letters.

[6]  Yin-Tsung Hwang,et al.  Simulated evolution based code generation for programmable DSP processors , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[7]  Raymond S. K. Kwan,et al.  A fuzzy simulated evolution algorithm for the driver scheduling problem , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[8]  Sadiq M. Sait,et al.  Topology design of switched enterprise networks using a fuzzy simulated evolution algorithm , 2002 .

[9]  Raymond S. K. Kwan,et al.  A fuzzy evolutionary approach with Taguchi parameter setting for the set covering problem , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[10]  Sadiq M. Sait,et al.  A simulated evolution approach to task matching and scheduling in heterogeneous computing environments , 2002 .

[11]  Alice E. Smith,et al.  Reliability estimation of computer communication networks: ANN models , 2003, Proceedings of the Eighth IEEE Symposium on Computers and Communications. ISCC 2003.

[12]  Sadiq M. Sait,et al.  Evaluating parallel simulated evolution strategies for VLSI cell placement , 2006, Proceedings 20th IEEE International Parallel & Distributed Processing Symposium.

[13]  Zubair A. Baig,et al.  A Simulated Evolution-Tabu search hybrid metaheuristic for routing in computer networks , 2007, 2007 IEEE Congress on Evolutionary Computation.

[14]  Andries Petrus Engelbrecht,et al.  A new fuzzy operator and its application to topology design of distributed local area networks , 2007, Inf. Sci..

[15]  Andries Petrus Engelbrecht,et al.  A fuzzy ant colony optimization algorithm for topology design of distributed local area networks , 2008, 2008 IEEE Swarm Intelligence Symposium.

[16]  Yih-Lang Li,et al.  Efficient simulated evolution based rerouting and congestion-relaxed layer assignment on 3-D global routing , 2009, 2009 Asia and South Pacific Design Automation Conference.

[17]  Andries Petrus Engelbrecht,et al.  Fuzzy hybrid simulated annealing algorithms for topology design of switched local area networks , 2009, Soft Comput..

[18]  Andries Petrus Engelbrecht,et al.  A fuzzy particle swarm optimization algorithm for computer communication network topology design , 2010, Applied Intelligence.