Stellar evolution models with overshooting based on 3-equation non-local theories I. Physical basis and the computation of the dissipation rate

Context. Mixing by convective overshooting has long been suggested to play an important role in the amount of hydrogen available for nuclear burning in convective cores of stars. The best way to model this effect is still debated. Aims. We suggest an improved model for the computation of the dissipation rate of turbulent kinetic energy which can be used in non-local models of stellar convection and can readily be implemented and self-consistently used in 1D stellar evolution calculations. Methods. We review the physics underlying various models to compute the dissipation rate of turbulent kinetic energy, epsilon, in local models of convection in stellar astrophysics and particularly in non-local ones. The different contributions to the dissipation rate and their dependence on local stratification and on non-local transport are analysed and a new method to account for at least some of these physical mechanisms is suggested. Results. We show how the new approach influences predictions of stellar models of intermediate-mass main-sequence stars and how these changes differ from other modifications of the non-local convection model that focus on the ratio of horizontal to vertical (turbulent) kinetic energy. Conclusions. The new model is shown to allow for a physically more complete description of convective overshooting and mixing in massive stars. Dissipation by buoyancy waves is found to be a key ingredient which has to be accounted for in non-local models of turbulent convection.