Local Search Approach to Genetic Programming for RF-PAs Modeling Implemented in FPGA J.R. C´ ardenas Valdez, Emigdio Z-Flores, Jos´ e Nu ˜ nez and Leonardo Trujillo Abstract This paper presents a genetic programming (GP) approach enhanced with a local search heuristic (GP-LS) to emulate the Doherty 7W @2.11 GHz Radio Fre- quency (RF) Power Amplifier (PA) conversion curves. GP has been shown to be a powerful modeling tool, but can be compromised by slow convergence and com- putational cost. The proposal is to combine the explorative search of standard GP, which build the syntax of the solution, with numerical methods that perform an ex- ploitative and greedy local optimization of the evolved structures. The results are compared with traditional modeling techniques, particularly the memory polyno- mial model (MPM). The main contribution of the paper is the design, comparison and hardware emulation of GP-LS for FPGA real applications. The experimental results show that GP-LS can outperform standard MPM, and suggest a promising new direction of future work on digital pre-distortion (DPD) that requires complex behavioral models. Key words: Behavioral models, DPD, FPGA, Genetic Programming, Local Search, MPM J.R. C´ ardenas Valdez Departamento de Ingenier´ ıa El´ ectrica y Electr´ onica, Instituto Tecnol´ ogico de Tijuana, Tijuana B.C., Mexico, e-mail: jose.cardenas@tectijuana.edu.mx Emigdio Z-Flores Departamento de Ingenier´ ıa El´ ectrica y Electr´ onica, Instituto Tecnol´ ogico de Tijuana, Tijuana B.C., Mexico, e-mail: emigdioz@gmail.com Leonardo Trujillo Departamento de Ingenier´ ıa El´ ectrica y Electr´ onica, Instituto Tecnol´ ogico de Tijuana, Tijuana B.C., Mexico, e-mail: leonardo.trujillo@tectijuana.edu.mx Jos´ e Nu ˜ nez Instituto Polit´ ecnico Nacional, Centro de Investigaci´ on y Desarrollo de Tecnolog´ ıa Digital, Tijuana B.C., Mexico, e-mail: nunez@cited.mx 1