Millimeter wave (mmWave) technology have attracted significant interest due to bandwidth availability improvement offering huge amount of spectrum to fifth generation (5G). The shorter wavelength of mmWave signals allows for greater data transmission rates and bandwidth, but it also makes them more
susceptible to various forms of attenuation and absorption between the transmitting and the receiving antennas, also referred to as path losses. The path loss model is an important tool in wireless network planning; allowing network planner to optimize the cell towers distribution and meet expected service level requirements. However, each type of path loss propagation model is designed to predict path loss in a particular environment that may be inaccurate in other different environment. Improving the existing models and developing new models are is vital for characterizing the wireless communication channel in both indoor and outdoor environments. This paper presents an efficient and novel path loss model based on polynomial regression analysis for predicting signal strength in millimeter bands. A genetic algorithm is used to optimize the parameters of the polynomial regression model by minimizing the sum of squared errors of the proposed model of path loss. The performance and accuracy of the polynomial regression model are evaluated and compared to both the measured path loss values and those obtained by lognormal shadowing model. The results show the close fit of the polynomial model to the field measurements with significantly lower root mean square error (RMSE) compared to the distance-shadowing model which proves the validity and accuracy of the proposed model.