Load forecasting is an essential component for operating and planning power systems. There are various prediction time horizons in accordance with applications. This paper proposes a forecasting model for mid-term load forecasting which is used for planning electricity supply and demand, electrical equipment maintenance schedule, and demand response programs. This paper presents weekly peak load forecasting method using time series and temperature sensitivity model with temperature stochastic modeling. Using Monte-Carlo simulation, the proposed method can also make probability distribution of weekly peak loads. The results of case studies show the effectiveness of the proposed load forecasting method.