The severe air condition with fog and haze presents a challenge to power system short-term load forecasting. Basing on existing human body amenity indicator, a new concept of human body amenity considering AQI, temperature, humidity and wind was presented while analytic hierarchy process(AHP) &Entropy were used to construct the human comfort index model considering temporal-spatial distribution. After that, a new arithmetic of random forests was adopted in building forecasting model, in which an optimized d...