Economic and environmental load dispatch aims to determine the amount of electricity generated from power plants to meet load demand while minimizing fossil fuel costs and air pollution emissions subject to operational and licensing requirements. These two schedu ling problems are commonly formulated with non-smooth cost functions respectively con-sidering various effects and constraints, such as the valve pointeffect, power balance and ramp rate limits. The expected increasein plug-in electric vehicles is li kely to see a significant impact onthe power system due to high charging power consumption and significant uncertainty in charging times. In this paper, multiple electric vehicle charging profil es are comparatively integratedinto a 24-hour load demand in an economic and environment dispatch model. Self-learning t eaching-learning based optimization (TLBO) is employed to solve the non-convex non-linear dispatch problems. Numerical results on well-known bench mark functions, as well as test systems with different scales of generation units show the significance of the new scheduling method.