Abstract: The recent development of the Energy Internet has urged the conventional inefficient utilization of single energy to change towards the more developed energy usage of optimal dispatch of the multi-energy system.Against the above-mentioned background,an optimal joint dispatch of multi-energy system model framework is firstly proposed based on the energy hub modeling approach.Then a typical multi-energy system model is developed considering carbon emission and energy supply costs with valve point effect.To solve this non-linear problem with non-convex,discontinuously differentiable characteristic,the cascaded algorithm combined with the knowledge transfer based Q-learning algorithm and interior point method is applied on the model.That is,the active power of generators is taken as an action variable of Q-learning in the upper structure and solve the multi-energy system model with the interior point method in the lower structure.Meanwhile,the efficiency is greatly improved by knowledge transfer.Case studies have been carried out on a 33 energy hubs test system to verify the effectiveness of the proposed model and algorithm.