Because of thermal inertia, the electric load is affected by the current temperatures as well as historical temperatures. This paper proposes a thermal inertia modeling method for the electric load to reduce forecasting error. In the proposed method, the relationship between the load and the temperature is established based on the discrete‐time inertia system model, in which the key parameters are obtained by particle swarm optimization (PSO). Test results show that the proposed method can model the thermal inertia well and improve the accuracy of electric load forecasting. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.