The article proposes a genetic algorithm for solving the problem of minimizing the mass of a plane truss, taking into account the variability of the cross-sectional area. The minimum mass of the steel structure is also low CO2 emission. The design is optimized using an efficient algorithm called Teaching Learning Based Optimization. The TLBO process is divided into two parts: the first consists of the “teacher phase” and the second consists of the “student phase”. The calculations are performed with the help of the finite element method program coded in MATLAB.